Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3498 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4141. Min Range: -3.4141
Max Act: 3.4141. Min Act: -0.1700
Data Index: 6557012 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4141. Min Range: -3.4141
Max Act: 3.3200. Min Act: -0.1700
Data Index: 5035870 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4141. Min Range: -3.4141
Max Act: 3.3200. Min Act: -0.1700
Data Index: 3546443 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4141. Min Range: -3.4141
Max Act: 3.3200. Min Act: -0.1700
Data Index: 8107142 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4141. Min Range: -3.4141
Max Act: 3.3200. Min Act: -0.1700
Data Index: 7176735 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4141. Min Range: -3.4141
Max Act: 3.3200. Min Act: -0.1700
Data Index: 4896967 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4141. Min Range: -3.4141
Max Act: 3.3200. Min Act: -0.1700
Data Index: 4232135 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4141. Min Range: -3.4141
Max Act: 3.2572. Min Act: -0.1700
Data Index: 3254382 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4141. Min Range: -3.4141
Max Act: 3.2572. Min Act: -0.1700
Data Index: 2836848 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4141. Min Range: -3.4141
Max Act: 3.2572. Min Act: -0.1700
Data Index: 8450483 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4141. Min Range: -3.4141
Max Act: 3.2572. Min Act: -0.1700
Data Index: 4259318 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4141. Min Range: -3.4141
Max Act: 3.2572. Min Act: -0.1700
Data Index: 8059693 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4141. Min Range: -3.4141
Max Act: 3.2572. Min Act: -0.1700
Data Index: 7738281 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4141. Min Range: -3.4141
Max Act: 3.2572. Min Act: -0.1700
Data Index: 3830987 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4141. Min Range: -3.4141
Max Act: 3.2886. Min Act: -0.1700
Data Index: 7202076 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4141. Min Range: -3.4141
Max Act: 3.2572. Min Act: -0.1700
Data Index: 6330448 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4141. Min Range: -3.4141
Max Act: 3.2258. Min Act: -0.1700
Data Index: 3717580 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4141. Min Range: -3.4141
Max Act: 3.2572. Min Act: -0.1700
Data Index: 6021118 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4141. Min Range: -3.4141
Max Act: 3.2572. Min Act: -0.1700
Data Index: 5411066 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4141. Min Range: -3.4141
Max Act: 3.2258. Min Act: -0.1700
Data Index: 4478029 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19