Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2970 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0330. Min Range: -8.0330
Max Act: 8.0330. Min Act: -0.1700
Data Index: 7744860 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0330. Min Range: -8.0330
Max Act: 7.8455. Min Act: -0.1700
Data Index: 6397732 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0330. Min Range: -8.0330
Max Act: 7.8143. Min Act: -0.1700
Data Index: 295956 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0330. Min Range: -8.0330
Max Act: 7.7205. Min Act: -0.1700
Data Index: 1232185 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0330. Min Range: -8.0330
Max Act: 7.7205. Min Act: -0.1700
Data Index: 3025110 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0330. Min Range: -8.0330
Max Act: 7.4705. Min Act: -0.1700
Data Index: 5436898 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0330. Min Range: -8.0330
Max Act: 7.4080. Min Act: -0.1700
Data Index: 1211564 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0330. Min Range: -8.0330
Max Act: 7.4080. Min Act: -0.1700
Data Index: 2365925 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0330. Min Range: -8.0330
Max Act: 7.3143. Min Act: -0.1700
Data Index: 5003292 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0330. Min Range: -8.0330
Max Act: 7.2518. Min Act: -0.1700
Data Index: 838079 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0330. Min Range: -8.0330
Max Act: 7.1893. Min Act: -0.1700
Data Index: 6905495 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0330. Min Range: -8.0330
Max Act: 7.0955. Min Act: -0.1700
Data Index: 4406094 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0330. Min Range: -8.0330
Max Act: 7.0643. Min Act: -0.1700
Data Index: 7859572 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0330. Min Range: -8.0330
Max Act: 7.0018. Min Act: -0.1700
Data Index: 571460 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0330. Min Range: -8.0330
Max Act: 7.0330. Min Act: -0.1700
Data Index: 1217975 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0330. Min Range: -8.0330
Max Act: 7.0018. Min Act: -0.1700
Data Index: 4537616 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0330. Min Range: -8.0330
Max Act: 7.0018. Min Act: -0.1700
Data Index: 3990140 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0330. Min Range: -8.0330
Max Act: 7.0018. Min Act: -0.1700
Data Index: 5046173 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0330. Min Range: -8.0330
Max Act: 7.0330. Min Act: -0.1700
Data Index: 4105324 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0330. Min Range: -8.0330
Max Act: 7.0018. Min Act: -0.1700
Data Index: 6160909 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #19