Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 23 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9307. Min Range: -6.9307
Max Act: 6.9307. Min Act: -0.1700
Data Index: 2875476 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9307. Min Range: -6.9307
Max Act: 6.7744. Min Act: -0.1700
Data Index: 3784970 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9307. Min Range: -6.9307
Max Act: 6.7432. Min Act: -0.1700
Data Index: 7321616 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9307. Min Range: -6.9307
Max Act: 6.7119. Min Act: -0.1700
Data Index: 4275716 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9307. Min Range: -6.9307
Max Act: 6.7119. Min Act: -0.1700
Data Index: 2485784 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9307. Min Range: -6.9307
Max Act: 6.5869. Min Act: -0.1700
Data Index: 909134 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9307. Min Range: -6.9307
Max Act: 6.5869. Min Act: -0.1700
Data Index: 3363299 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9307. Min Range: -6.9307
Max Act: 6.5244. Min Act: -0.1700
Data Index: 3991483 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9307. Min Range: -6.9307
Max Act: 6.5557. Min Act: -0.1700
Data Index: 412745 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9307. Min Range: -6.9307
Max Act: 6.5557. Min Act: -0.1700
Data Index: 8069123 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9307. Min Range: -6.9307
Max Act: 6.4932. Min Act: -0.1700
Data Index: 4292135 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9307. Min Range: -6.9307
Max Act: 6.4307. Min Act: -0.1700
Data Index: 5515282 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9307. Min Range: -6.9307
Max Act: 6.3682. Min Act: -0.1700
Data Index: 1412208 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9307. Min Range: -6.9307
Max Act: 6.3994. Min Act: -0.1700
Data Index: 104737 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9307. Min Range: -6.9307
Max Act: 6.3682. Min Act: -0.1700
Data Index: 4964394 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9307. Min Range: -6.9307
Max Act: 6.3369. Min Act: -0.1700
Data Index: 5091186 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9307. Min Range: -6.9307
Max Act: 6.3369. Min Act: -0.1700
Data Index: 282597 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9307. Min Range: -6.9307
Max Act: 6.2744. Min Act: -0.1700
Data Index: 1414893 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9307. Min Range: -6.9307
Max Act: 6.3057. Min Act: -0.1700
Data Index: 2032192 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9307. Min Range: -6.9307
Max Act: 6.3057. Min Act: -0.1700
Data Index: 209198 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #19