Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3240 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 17.6247. Min Range: -17.6247
Max Act: 17.6247. Min Act: -0.1700
Data Index: 4435450 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 17.6247. Min Range: -17.6247
Max Act: 17.4997. Min Act: -0.1700
Data Index: 1083544 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 17.6247. Min Range: -17.6247
Max Act: 17.4997. Min Act: -0.1697
Data Index: 7854988 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 17.6247. Min Range: -17.6247
Max Act: 17.4997. Min Act: -0.1700
Data Index: 8240707 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 17.6247. Min Range: -17.6247
Max Act: 17.4997. Min Act: -0.1700
Data Index: 2826394 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 17.6247. Min Range: -17.6247
Max Act: 17.3747. Min Act: -0.1700
Data Index: 4230834 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 17.6247. Min Range: -17.6247
Max Act: 17.3747. Min Act: -0.1700
Data Index: 1671411 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 17.6247. Min Range: -17.6247
Max Act: 17.1247. Min Act: -0.1699
Data Index: 842727 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 17.6247. Min Range: -17.6247
Max Act: 17.2497. Min Act: -0.1700
Data Index: 7098034 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 17.6247. Min Range: -17.6247
Max Act: 17.2497. Min Act: -0.1683
Data Index: 5161842 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 17.6247. Min Range: -17.6247
Max Act: 17.1247. Min Act: -0.1700
Data Index: 6535514 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 17.6247. Min Range: -17.6247
Max Act: 17.1247. Min Act: -0.1700
Data Index: 2140003 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 17.6247. Min Range: -17.6247
Max Act: 17.1247. Min Act: -0.1699
Data Index: 2833769 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 17.6247. Min Range: -17.6247
Max Act: 17.1247. Min Act: -0.1699
Data Index: 8240708 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 17.6247. Min Range: -17.6247
Max Act: 17.1247. Min Act: -0.1700
Data Index: 7686724 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 17.6247. Min Range: -17.6247
Max Act: 17.1247. Min Act: -0.1699
Data Index: 2452944 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 17.6247. Min Range: -17.6247
Max Act: 16.9997. Min Act: -0.1700
Data Index: 3797975 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 17.6247. Min Range: -17.6247
Max Act: 16.9997. Min Act: -0.1700
Data Index: 6467352 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 17.6247. Min Range: -17.6247
Max Act: 16.9997. Min Act: -0.1700
Data Index: 3112338 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 17.6247. Min Range: -17.6247
Max Act: 16.9997. Min Act: -0.1693
Data Index: 3315796 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #19