Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3095 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9034. Min Range: -4.9034
Max Act: 4.9034. Min Act: -0.1700
Data Index: 2466712 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9034. Min Range: -4.9034
Max Act: 4.8721. Min Act: -0.1700
Data Index: 1155984 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9034. Min Range: -4.9034
Max Act: 4.7471. Min Act: -0.1700
Data Index: 2804906 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9034. Min Range: -4.9034
Max Act: 4.7471. Min Act: -0.1700
Data Index: 6073802 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9034. Min Range: -4.9034
Max Act: 4.7159. Min Act: -0.1700
Data Index: 1298321 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9034. Min Range: -4.9034
Max Act: 4.6846. Min Act: -0.1700
Data Index: 708806 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9034. Min Range: -4.9034
Max Act: 4.6534. Min Act: -0.1700
Data Index: 4403082 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9034. Min Range: -4.9034
Max Act: 4.5909. Min Act: -0.1700
Data Index: 763639 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9034. Min Range: -4.9034
Max Act: 4.5596. Min Act: -0.1700
Data Index: 8114440 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9034. Min Range: -4.9034
Max Act: 4.5284. Min Act: -0.1700
Data Index: 4180330 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9034. Min Range: -4.9034
Max Act: 4.5284. Min Act: -0.1700
Data Index: 8678529 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9034. Min Range: -4.9034
Max Act: 4.5284. Min Act: -0.1700
Data Index: 150568 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9034. Min Range: -4.9034
Max Act: 4.4971. Min Act: -0.1700
Data Index: 1606135 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9034. Min Range: -4.9034
Max Act: 4.4971. Min Act: -0.1700
Data Index: 5371575 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9034. Min Range: -4.9034
Max Act: 4.4971. Min Act: -0.1700
Data Index: 4016276 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9034. Min Range: -4.9034
Max Act: 4.4971. Min Act: -0.1700
Data Index: 8301729 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9034. Min Range: -4.9034
Max Act: 4.4971. Min Act: -0.1700
Data Index: 5552098 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9034. Min Range: -4.9034
Max Act: 4.4659. Min Act: -0.1700
Data Index: 6474435 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9034. Min Range: -4.9034
Max Act: 4.4659. Min Act: -0.1700
Data Index: 2798296 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9034. Min Range: -4.9034
Max Act: 4.4346. Min Act: -0.1700
Data Index: 8805661 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #19