Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2851 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5145. Min Range: -7.5145
Max Act: 7.5145. Min Act: -0.1700
Data Index: 5009425 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5145. Min Range: -7.5145
Max Act: 7.4833. Min Act: -0.1700
Data Index: 4733168 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5145. Min Range: -7.5145
Max Act: 7.4520. Min Act: -0.1700
Data Index: 2388320 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5145. Min Range: -7.5145
Max Act: 7.4833. Min Act: -0.1700
Data Index: 8472573 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5145. Min Range: -7.5145
Max Act: 7.4520. Min Act: -0.1700
Data Index: 994402 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5145. Min Range: -7.5145
Max Act: 7.4208. Min Act: -0.1700
Data Index: 4845078 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5145. Min Range: -7.5145
Max Act: 7.3270. Min Act: -0.1700
Data Index: 7900461 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5145. Min Range: -7.5145
Max Act: 7.2958. Min Act: -0.1700
Data Index: 3417000 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5145. Min Range: -7.5145
Max Act: 7.3270. Min Act: -0.1700
Data Index: 3490567 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5145. Min Range: -7.5145
Max Act: 7.3583. Min Act: -0.1700
Data Index: 7265084 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5145. Min Range: -7.5145
Max Act: 7.2958. Min Act: -0.1700
Data Index: 5725324 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5145. Min Range: -7.5145
Max Act: 7.2645. Min Act: -0.1700
Data Index: 8581082 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5145. Min Range: -7.5145
Max Act: 7.2333. Min Act: -0.1700
Data Index: 1034836 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5145. Min Range: -7.5145
Max Act: 7.2645. Min Act: -0.1700
Data Index: 4089117 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5145. Min Range: -7.5145
Max Act: 7.2333. Min Act: -0.1700
Data Index: 3669610 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5145. Min Range: -7.5145
Max Act: 7.2020. Min Act: -0.1700
Data Index: 6868589 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5145. Min Range: -7.5145
Max Act: 7.1395. Min Act: -0.1700
Data Index: 8329816 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5145. Min Range: -7.5145
Max Act: 7.2020. Min Act: -0.1700
Data Index: 4626474 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5145. Min Range: -7.5145
Max Act: 7.1708. Min Act: -0.1700
Data Index: 197204 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5145. Min Range: -7.5145
Max Act: 7.1083. Min Act: -0.1700
Data Index: 2485203 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #19