Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2598 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4296. Min Range: -4.4296
Max Act: 4.4296. Min Act: -0.1700
Data Index: 285439 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4296. Min Range: -4.4296
Max Act: 4.3983. Min Act: -0.1700
Data Index: 1146415 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4296. Min Range: -4.4296
Max Act: 4.3671. Min Act: -0.1700
Data Index: 3089829 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4296. Min Range: -4.4296
Max Act: 4.3046. Min Act: -0.1700
Data Index: 1476029 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4296. Min Range: -4.4296
Max Act: 4.2733. Min Act: -0.1700
Data Index: 5074652 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4296. Min Range: -4.4296
Max Act: 4.2733. Min Act: -0.1700
Data Index: 765617 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4296. Min Range: -4.4296
Max Act: 4.2421. Min Act: -0.1700
Data Index: 896169 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4296. Min Range: -4.4296
Max Act: 4.2421. Min Act: -0.1700
Data Index: 7047997 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4296. Min Range: -4.4296
Max Act: 4.2108. Min Act: -0.1700
Data Index: 5080266 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4296. Min Range: -4.4296
Max Act: 4.2108. Min Act: -0.1700
Data Index: 6750821 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4296. Min Range: -4.4296
Max Act: 4.2108. Min Act: -0.1700
Data Index: 1173731 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4296. Min Range: -4.4296
Max Act: 4.2108. Min Act: -0.1700
Data Index: 7859239 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4296. Min Range: -4.4296
Max Act: 4.1483. Min Act: -0.1700
Data Index: 8377013 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4296. Min Range: -4.4296
Max Act: 4.1483. Min Act: -0.1700
Data Index: 2700038 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4296. Min Range: -4.4296
Max Act: 4.1796. Min Act: -0.1700
Data Index: 4403218 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4296. Min Range: -4.4296
Max Act: 4.2108. Min Act: -0.1700
Data Index: 6084346 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4296. Min Range: -4.4296
Max Act: 4.1483. Min Act: -0.1700
Data Index: 4122085 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4296. Min Range: -4.4296
Max Act: 4.1483. Min Act: -0.1700
Data Index: 2410756 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4296. Min Range: -4.4296
Max Act: 4.1483. Min Act: -0.1700
Data Index: 4973511 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4296. Min Range: -4.4296
Max Act: 4.1483. Min Act: -0.1700
Data Index: 150614 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19