Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1562 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7163. Min Range: -8.7163
Max Act: 8.7163. Min Act: -0.1700
Data Index: 6734917 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7163. Min Range: -8.7163
Max Act: 8.5913. Min Act: -0.1700
Data Index: 1226702 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7163. Min Range: -8.7163
Max Act: 8.4038. Min Act: -0.1700
Data Index: 3125516 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7163. Min Range: -8.7163
Max Act: 8.2788. Min Act: -0.1700
Data Index: 585369 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7163. Min Range: -8.7163
Max Act: 8.2788. Min Act: -0.1700
Data Index: 2693844 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7163. Min Range: -8.7163
Max Act: 8.1538. Min Act: -0.1700
Data Index: 111386 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7163. Min Range: -8.7163
Max Act: 8.0288. Min Act: -0.1700
Data Index: 5639104 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7163. Min Range: -8.7163
Max Act: 8.0913. Min Act: -0.1700
Data Index: 3566217 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7163. Min Range: -8.7163
Max Act: 7.9663. Min Act: -0.1700
Data Index: 5191630 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7163. Min Range: -8.7163
Max Act: 7.9663. Min Act: -0.1700
Data Index: 4586352 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7163. Min Range: -8.7163
Max Act: 7.9663. Min Act: -0.1700
Data Index: 6881713 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7163. Min Range: -8.7163
Max Act: 7.9038. Min Act: -0.1700
Data Index: 8659 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7163. Min Range: -8.7163
Max Act: 7.9038. Min Act: -0.1700
Data Index: 3930386 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7163. Min Range: -8.7163
Max Act: 7.8413. Min Act: -0.1700
Data Index: 6671461 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7163. Min Range: -8.7163
Max Act: 7.8413. Min Act: -0.1700
Data Index: 5601912 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7163. Min Range: -8.7163
Max Act: 7.8413. Min Act: -0.1700
Data Index: 4224304 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7163. Min Range: -8.7163
Max Act: 7.8413. Min Act: -0.1700
Data Index: 6788110 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7163. Min Range: -8.7163
Max Act: 7.8413. Min Act: -0.1700
Data Index: 7526351 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7163. Min Range: -8.7163
Max Act: 7.7788. Min Act: -0.1700
Data Index: 1212603 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7163. Min Range: -8.7163
Max Act: 7.7788. Min Act: -0.1700
Data Index: 4728869 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #19