Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2951 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6136. Min Range: -7.6136
Max Act: 7.6136. Min Act: -0.1700
Data Index: 3149476 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6136. Min Range: -7.6136
Max Act: 7.5511. Min Act: -0.1700
Data Index: 4825465 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6136. Min Range: -7.6136
Max Act: 7.5199. Min Act: -0.1700
Data Index: 5409402 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6136. Min Range: -7.6136
Max Act: 7.2386. Min Act: -0.1700
Data Index: 2017951 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6136. Min Range: -7.6136
Max Act: 7.0824. Min Act: -0.1700
Data Index: 3641974 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6136. Min Range: -7.6136
Max Act: 7.0511. Min Act: -0.1700
Data Index: 1324570 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6136. Min Range: -7.6136
Max Act: 7.0199. Min Act: -0.1700
Data Index: 5836085 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6136. Min Range: -7.6136
Max Act: 6.9261. Min Act: -0.1700
Data Index: 5934702 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6136. Min Range: -7.6136
Max Act: 6.9261. Min Act: -0.1700
Data Index: 7096683 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6136. Min Range: -7.6136
Max Act: 6.8949. Min Act: -0.1700
Data Index: 2760158 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6136. Min Range: -7.6136
Max Act: 6.8949. Min Act: -0.1700
Data Index: 3589950 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6136. Min Range: -7.6136
Max Act: 6.8636. Min Act: -0.1700
Data Index: 97741 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6136. Min Range: -7.6136
Max Act: 6.8636. Min Act: -0.1700
Data Index: 1749571 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6136. Min Range: -7.6136
Max Act: 6.8636. Min Act: -0.1700
Data Index: 3924482 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6136. Min Range: -7.6136
Max Act: 6.8324. Min Act: -0.1700
Data Index: 5786594 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6136. Min Range: -7.6136
Max Act: 6.8324. Min Act: -0.1700
Data Index: 682578 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6136. Min Range: -7.6136
Max Act: 6.8011. Min Act: -0.1700
Data Index: 1637621 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6136. Min Range: -7.6136
Max Act: 6.8011. Min Act: -0.1700
Data Index: 6821080 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6136. Min Range: -7.6136
Max Act: 6.8011. Min Act: -0.1700
Data Index: 2693004 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6136. Min Range: -7.6136
Max Act: 6.7699. Min Act: -0.1700
Data Index: 6325375 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #19