Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5029 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6168. Min Range: -4.6168
Max Act: 4.6168. Min Act: -0.1700
Data Index: 6190796 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6168. Min Range: -4.6168
Max Act: 4.5230. Min Act: -0.1700
Data Index: 7404366 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6168. Min Range: -4.6168
Max Act: 4.5230. Min Act: -0.1700
Data Index: 4284495 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6168. Min Range: -4.6168
Max Act: 4.5230. Min Act: -0.1700
Data Index: 3054040 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6168. Min Range: -4.6168
Max Act: 4.4917. Min Act: -0.1700
Data Index: 6258710 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6168. Min Range: -4.6168
Max Act: 4.4605. Min Act: -0.1700
Data Index: 4470874 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6168. Min Range: -4.6168
Max Act: 4.4605. Min Act: -0.1700
Data Index: 6708701 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6168. Min Range: -4.6168
Max Act: 4.4605. Min Act: -0.1700
Data Index: 6200345 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6168. Min Range: -4.6168
Max Act: 4.4605. Min Act: -0.1700
Data Index: 4958374 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6168. Min Range: -4.6168
Max Act: 4.4605. Min Act: -0.1699
Data Index: 5604381 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6168. Min Range: -4.6168
Max Act: 4.4292. Min Act: -0.1700
Data Index: 7405068 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6168. Min Range: -4.6168
Max Act: 4.4292. Min Act: -0.1700
Data Index: 2479244 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6168. Min Range: -4.6168
Max Act: 4.4605. Min Act: -0.1700
Data Index: 8345449 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6168. Min Range: -4.6168
Max Act: 4.4292. Min Act: -0.1700
Data Index: 570180 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6168. Min Range: -4.6168
Max Act: 4.4292. Min Act: -0.1700
Data Index: 4864904 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6168. Min Range: -4.6168
Max Act: 4.3980. Min Act: -0.1700
Data Index: 5929560 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6168. Min Range: -4.6168
Max Act: 4.3980. Min Act: -0.1700
Data Index: 5358401 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6168. Min Range: -4.6168
Max Act: 4.3980. Min Act: -0.1700
Data Index: 3713623 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6168. Min Range: -4.6168
Max Act: 4.3980. Min Act: -0.1700
Data Index: 6369690 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6168. Min Range: -4.6168
Max Act: 4.3980. Min Act: -0.1700
Data Index: 3837228 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #19