Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5013 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.6786. Min Range: -8.6786
Max Act: 8.6786. Min Act: -0.1700
Data Index: 5860167 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6786. Min Range: -8.6786
Max Act: 8.4286. Min Act: -0.1700
Data Index: 6505634 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6786. Min Range: -8.6786
Max Act: 8.1161. Min Act: -0.1700
Data Index: 1099912 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6786. Min Range: -8.6786
Max Act: 8.0536. Min Act: -0.1700
Data Index: 5482346 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6786. Min Range: -8.6786
Max Act: 8.0536. Min Act: -0.1700
Data Index: 2516474 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6786. Min Range: -8.6786
Max Act: 7.9911. Min Act: -0.1700
Data Index: 917395 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6786. Min Range: -8.6786
Max Act: 7.9911. Min Act: -0.1700
Data Index: 7057689 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6786. Min Range: -8.6786
Max Act: 7.9286. Min Act: -0.1700
Data Index: 1181057 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6786. Min Range: -8.6786
Max Act: 7.8661. Min Act: -0.1700
Data Index: 7051177 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6786. Min Range: -8.6786
Max Act: 7.8661. Min Act: -0.1700
Data Index: 7258535 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6786. Min Range: -8.6786
Max Act: 7.8661. Min Act: -0.1700
Data Index: 3340114 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6786. Min Range: -8.6786
Max Act: 7.8036. Min Act: -0.1700
Data Index: 1024190 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6786. Min Range: -8.6786
Max Act: 7.7411. Min Act: -0.1700
Data Index: 4845612 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6786. Min Range: -8.6786
Max Act: 7.7411. Min Act: -0.1700
Data Index: 5190876 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6786. Min Range: -8.6786
Max Act: 7.7411. Min Act: -0.1700
Data Index: 3732528 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6786. Min Range: -8.6786
Max Act: 7.7411. Min Act: -0.1700
Data Index: 1166280 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6786. Min Range: -8.6786
Max Act: 7.8036. Min Act: -0.1700
Data Index: 5996145 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6786. Min Range: -8.6786
Max Act: 7.6786. Min Act: -0.1700
Data Index: 3762701 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6786. Min Range: -8.6786
Max Act: 7.7099. Min Act: -0.1700
Data Index: 5043295 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6786. Min Range: -8.6786
Max Act: 7.7099. Min Act: -0.1700
Data Index: 1832800 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #19