Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2935 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4214. Min Range: -8.4214
Max Act: 8.4214. Min Act: -0.1700
Data Index: 48016 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4214. Min Range: -8.4214
Max Act: 8.1089. Min Act: -0.1700
Data Index: 3684449 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4214. Min Range: -8.4214
Max Act: 7.8589. Min Act: -0.1700
Data Index: 3202259 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4214. Min Range: -8.4214
Max Act: 7.8589. Min Act: -0.1700
Data Index: 3244483 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4214. Min Range: -8.4214
Max Act: 7.7964. Min Act: -0.1700
Data Index: 784454 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4214. Min Range: -8.4214
Max Act: 7.7339. Min Act: -0.1700
Data Index: 1493240 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4214. Min Range: -8.4214
Max Act: 7.7339. Min Act: -0.1700
Data Index: 3116683 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4214. Min Range: -8.4214
Max Act: 7.7339. Min Act: -0.1700
Data Index: 4813906 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4214. Min Range: -8.4214
Max Act: 7.7339. Min Act: -0.1700
Data Index: 6208045 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4214. Min Range: -8.4214
Max Act: 7.6714. Min Act: -0.1700
Data Index: 6170536 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4214. Min Range: -8.4214
Max Act: 7.6089. Min Act: -0.1700
Data Index: 3670920 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4214. Min Range: -8.4214
Max Act: 7.6089. Min Act: -0.1700
Data Index: 2151226 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4214. Min Range: -8.4214
Max Act: 7.6089. Min Act: -0.1700
Data Index: 7771071 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4214. Min Range: -8.4214
Max Act: 7.6089. Min Act: -0.1700
Data Index: 6007393 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4214. Min Range: -8.4214
Max Act: 7.6089. Min Act: -0.1700
Data Index: 3311531 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4214. Min Range: -8.4214
Max Act: 7.5464. Min Act: -0.1700
Data Index: 7012659 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4214. Min Range: -8.4214
Max Act: 7.6089. Min Act: -0.1700
Data Index: 4878328 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4214. Min Range: -8.4214
Max Act: 7.6089. Min Act: -0.1700
Data Index: 3993183 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4214. Min Range: -8.4214
Max Act: 7.6714. Min Act: -0.1700
Data Index: 4646521 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4214. Min Range: -8.4214
Max Act: 7.6089. Min Act: -0.1700
Data Index: 3670931 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #19