Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3128 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.2145. Min Range: -3.2145
Max Act: 3.2145. Min Act: -0.1700
Data Index: 1595639 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2145. Min Range: -3.2145
Max Act: 3.1201. Min Act: -0.1700
Data Index: 6270491 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2145. Min Range: -3.2145
Max Act: 3.0728. Min Act: -0.1700
Data Index: 5904995 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2145. Min Range: -3.2145
Max Act: 3.0570. Min Act: -0.1700
Data Index: 86529 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2145. Min Range: -3.2145
Max Act: 3.0728. Min Act: -0.1700
Data Index: 6198363 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2145. Min Range: -3.2145
Max Act: 3.0728. Min Act: -0.1700
Data Index: 2114770 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2145. Min Range: -3.2145
Max Act: 3.0728. Min Act: -0.1700
Data Index: 2567425 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2145. Min Range: -3.2145
Max Act: 3.0570. Min Act: -0.1700
Data Index: 8029397 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2145. Min Range: -3.2145
Max Act: 3.0412. Min Act: -0.1700
Data Index: 7982442 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2145. Min Range: -3.2145
Max Act: 3.0412. Min Act: -0.1700
Data Index: 8060815 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2145. Min Range: -3.2145
Max Act: 3.0412. Min Act: -0.1700
Data Index: 2760604 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2145. Min Range: -3.2145
Max Act: 3.0254. Min Act: -0.1700
Data Index: 8633925 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2145. Min Range: -3.2145
Max Act: 3.0096. Min Act: -0.1700
Data Index: 7548672 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2145. Min Range: -3.2145
Max Act: 3.0254. Min Act: -0.1700
Data Index: 5420116 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2145. Min Range: -3.2145
Max Act: 3.0254. Min Act: -0.1700
Data Index: 4321708 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2145. Min Range: -3.2145
Max Act: 3.0254. Min Act: -0.1700
Data Index: 4829498 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2145. Min Range: -3.2145
Max Act: 3.0254. Min Act: -0.1700
Data Index: 1345479 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2145. Min Range: -3.2145
Max Act: 3.0096. Min Act: -0.1700
Data Index: 2558442 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2145. Min Range: -3.2145
Max Act: 3.0096. Min Act: -0.1700
Data Index: 6096500 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2145. Min Range: -3.2145
Max Act: 3.0096. Min Act: -0.1700
Data Index: 6182982 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19