Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3773 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5776. Min Range: -5.5776
Max Act: 5.5776. Min Act: -0.1700
Data Index: 7106900 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5776. Min Range: -5.5776
Max Act: 5.5151. Min Act: -0.1700
Data Index: 4762334 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5776. Min Range: -5.5776
Max Act: 5.4526. Min Act: -0.1700
Data Index: 8582140 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5776. Min Range: -5.5776
Max Act: 5.4838. Min Act: -0.1700
Data Index: 3243365 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5776. Min Range: -5.5776
Max Act: 5.4526. Min Act: -0.1700
Data Index: 5375679 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5776. Min Range: -5.5776
Max Act: 5.4526. Min Act: -0.1700
Data Index: 149940 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5776. Min Range: -5.5776
Max Act: 5.4526. Min Act: -0.1700
Data Index: 3203481 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5776. Min Range: -5.5776
Max Act: 5.4213. Min Act: -0.1700
Data Index: 524763 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5776. Min Range: -5.5776
Max Act: 5.4213. Min Act: -0.1700
Data Index: 8054683 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5776. Min Range: -5.5776
Max Act: 5.3276. Min Act: -0.1700
Data Index: 6608281 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5776. Min Range: -5.5776
Max Act: 5.3276. Min Act: -0.1700
Data Index: 6310050 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5776. Min Range: -5.5776
Max Act: 5.2651. Min Act: -0.1700
Data Index: 1617273 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5776. Min Range: -5.5776
Max Act: 5.2963. Min Act: -0.1700
Data Index: 2956065 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5776. Min Range: -5.5776
Max Act: 5.2651. Min Act: -0.1700
Data Index: 5184019 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5776. Min Range: -5.5776
Max Act: 5.2651. Min Act: -0.1700
Data Index: 7497854 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5776. Min Range: -5.5776
Max Act: 5.2651. Min Act: -0.1700
Data Index: 6530744 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5776. Min Range: -5.5776
Max Act: 5.2651. Min Act: -0.1700
Data Index: 2619181 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5776. Min Range: -5.5776
Max Act: 5.2651. Min Act: -0.1700
Data Index: 5311346 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5776. Min Range: -5.5776
Max Act: 5.2338. Min Act: -0.1700
Data Index: 4778056 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5776. Min Range: -5.5776
Max Act: 5.2338. Min Act: -0.1700
Data Index: 2584305 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #19