Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3656 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5899. Min Range: -3.5899
Max Act: 3.5899. Min Act: -0.1700
Data Index: 5318735 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5899. Min Range: -3.5899
Max Act: 3.5586. Min Act: -0.1700
Data Index: 846430 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5899. Min Range: -3.5899
Max Act: 3.5586. Min Act: -0.1700
Data Index: 7798497 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5899. Min Range: -3.5899
Max Act: 3.5586. Min Act: -0.1700
Data Index: 2877795 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5899. Min Range: -3.5899
Max Act: 3.5273. Min Act: -0.1700
Data Index: 7202064 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5899. Min Range: -3.5899
Max Act: 3.5430. Min Act: -0.1700
Data Index: 4415262 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5899. Min Range: -3.5899
Max Act: 3.5273. Min Act: -0.1700
Data Index: 3438449 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5899. Min Range: -3.5899
Max Act: 3.5116. Min Act: -0.1700
Data Index: 7339442 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5899. Min Range: -3.5899
Max Act: 3.5116. Min Act: -0.1700
Data Index: 3920516 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5899. Min Range: -3.5899
Max Act: 3.5116. Min Act: -0.1700
Data Index: 8058581 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5899. Min Range: -3.5899
Max Act: 3.4960. Min Act: -0.1700
Data Index: 1213950 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5899. Min Range: -3.5899
Max Act: 3.4960. Min Act: -0.1700
Data Index: 2626594 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5899. Min Range: -3.5899
Max Act: 3.4803. Min Act: -0.1700
Data Index: 3871616 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5899. Min Range: -3.5899
Max Act: 3.4803. Min Act: -0.1700
Data Index: 1940730 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5899. Min Range: -3.5899
Max Act: 3.4646. Min Act: -0.1700
Data Index: 8127211 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5899. Min Range: -3.5899
Max Act: 3.4803. Min Act: -0.1700
Data Index: 8026514 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5899. Min Range: -3.5899
Max Act: 3.4803. Min Act: -0.1700
Data Index: 4942191 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5899. Min Range: -3.5899
Max Act: 3.4646. Min Act: -0.1700
Data Index: 3198807 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5899. Min Range: -3.5899
Max Act: 3.4646. Min Act: -0.1700
Data Index: 2351721 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5899. Min Range: -3.5899
Max Act: 3.4646. Min Act: -0.1700
Data Index: 2391712 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #19