Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1827 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.2536. Min Range: -7.2536
Max Act: 7.2536. Min Act: -0.1700
Data Index: 8038520 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2536. Min Range: -7.2536
Max Act: 7.0661. Min Act: -0.1700
Data Index: 1318379 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2536. Min Range: -7.2536
Max Act: 7.0348. Min Act: -0.1700
Data Index: 1046850 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2536. Min Range: -7.2536
Max Act: 6.9098. Min Act: -0.1700
Data Index: 7328631 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2536. Min Range: -7.2536
Max Act: 6.8786. Min Act: -0.1700
Data Index: 2180651 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2536. Min Range: -7.2536
Max Act: 6.8161. Min Act: -0.1700
Data Index: 1922062 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2536. Min Range: -7.2536
Max Act: 6.8161. Min Act: -0.1700
Data Index: 475737 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2536. Min Range: -7.2536
Max Act: 6.8161. Min Act: -0.1700
Data Index: 2354108 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2536. Min Range: -7.2536
Max Act: 6.7536. Min Act: -0.1700
Data Index: 7038473 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2536. Min Range: -7.2536
Max Act: 6.7536. Min Act: -0.1700
Data Index: 3428767 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2536. Min Range: -7.2536
Max Act: 6.7223. Min Act: -0.1700
Data Index: 4213178 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2536. Min Range: -7.2536
Max Act: 6.6598. Min Act: -0.1699
Data Index: 5505006 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2536. Min Range: -7.2536
Max Act: 6.6598. Min Act: -0.1700
Data Index: 184626 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2536. Min Range: -7.2536
Max Act: 6.6598. Min Act: -0.1700
Data Index: 6111102 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2536. Min Range: -7.2536
Max Act: 6.6286. Min Act: -0.1700
Data Index: 316552 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2536. Min Range: -7.2536
Max Act: 6.6598. Min Act: -0.1700
Data Index: 7123770 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2536. Min Range: -7.2536
Max Act: 6.6598. Min Act: -0.1700
Data Index: 418170 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2536. Min Range: -7.2536
Max Act: 6.6598. Min Act: -0.1700
Data Index: 3964344 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2536. Min Range: -7.2536
Max Act: 6.6286. Min Act: -0.1700
Data Index: 7684518 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2536. Min Range: -7.2536
Max Act: 6.5973. Min Act: -0.1700
Data Index: 7397779 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #19