Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6289 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1677. Min Range: -6.1677
Max Act: 6.1677. Min Act: -0.1700
Data Index: 471478 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1677. Min Range: -6.1677
Max Act: 6.0115. Min Act: -0.1700
Data Index: 151071 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1677. Min Range: -6.1677
Max Act: 5.9802. Min Act: -0.1700
Data Index: 181334 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1677. Min Range: -6.1677
Max Act: 5.9802. Min Act: -0.1700
Data Index: 3162384 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1677. Min Range: -6.1677
Max Act: 5.9490. Min Act: -0.1700
Data Index: 6177680 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1677. Min Range: -6.1677
Max Act: 5.9490. Min Act: -0.1700
Data Index: 3115962 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1677. Min Range: -6.1677
Max Act: 5.9177. Min Act: -0.1700
Data Index: 4633257 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1677. Min Range: -6.1677
Max Act: 5.9177. Min Act: -0.1700
Data Index: 1262423 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1677. Min Range: -6.1677
Max Act: 5.8552. Min Act: -0.1700
Data Index: 5884386 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1677. Min Range: -6.1677
Max Act: 5.8552. Min Act: -0.1700
Data Index: 3701427 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1677. Min Range: -6.1677
Max Act: 5.8240. Min Act: -0.1700
Data Index: 8086166 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1677. Min Range: -6.1677
Max Act: 5.7927. Min Act: -0.1700
Data Index: 2636105 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1677. Min Range: -6.1677
Max Act: 5.7927. Min Act: -0.1700
Data Index: 8183969 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1677. Min Range: -6.1677
Max Act: 5.7615. Min Act: -0.1700
Data Index: 4145412 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1677. Min Range: -6.1677
Max Act: 5.7615. Min Act: -0.1700
Data Index: 59987 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1677. Min Range: -6.1677
Max Act: 5.7615. Min Act: -0.1700
Data Index: 391515 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1677. Min Range: -6.1677
Max Act: 5.7615. Min Act: -0.1700
Data Index: 7947090 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1677. Min Range: -6.1677
Max Act: 5.6990. Min Act: -0.1700
Data Index: 1271093 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1677. Min Range: -6.1677
Max Act: 5.7302. Min Act: -0.1700
Data Index: 341325 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1677. Min Range: -6.1677
Max Act: 5.7302. Min Act: -0.1700
Data Index: 6412628 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #19