Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 797 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1663. Min Range: -5.1663
Max Act: 5.1663. Min Act: -0.1700
Data Index: 4618094 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1663. Min Range: -5.1663
Max Act: 5.0725. Min Act: -0.1700
Data Index: 6750963 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1663. Min Range: -5.1663
Max Act: 5.0100. Min Act: -0.1700
Data Index: 1692406 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1663. Min Range: -5.1663
Max Act: 5.0100. Min Act: -0.1700
Data Index: 6388627 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1663. Min Range: -5.1663
Max Act: 4.9788. Min Act: -0.1700
Data Index: 2896963 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1663. Min Range: -5.1663
Max Act: 4.9788. Min Act: -0.1700
Data Index: 7380573 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1663. Min Range: -5.1663
Max Act: 4.9475. Min Act: -0.1700
Data Index: 2127394 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1663. Min Range: -5.1663
Max Act: 4.9163. Min Act: -0.1700
Data Index: 7108742 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1663. Min Range: -5.1663
Max Act: 4.9163. Min Act: -0.1700
Data Index: 3063749 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1663. Min Range: -5.1663
Max Act: 4.9163. Min Act: -0.1700
Data Index: 4019433 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1663. Min Range: -5.1663
Max Act: 4.8538. Min Act: -0.1700
Data Index: 6898363 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1663. Min Range: -5.1663
Max Act: 4.8850. Min Act: -0.1700
Data Index: 8241680 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1663. Min Range: -5.1663
Max Act: 4.8850. Min Act: -0.1700
Data Index: 1165262 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1663. Min Range: -5.1663
Max Act: 4.9163. Min Act: -0.1700
Data Index: 5368136 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1663. Min Range: -5.1663
Max Act: 4.8850. Min Act: -0.1700
Data Index: 4889784 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1663. Min Range: -5.1663
Max Act: 4.8225. Min Act: -0.1700
Data Index: 441715 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1663. Min Range: -5.1663
Max Act: 4.8538. Min Act: -0.1700
Data Index: 1008080 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1663. Min Range: -5.1663
Max Act: 4.8538. Min Act: -0.1700
Data Index: 6213390 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1663. Min Range: -5.1663
Max Act: 4.8538. Min Act: -0.1700
Data Index: 2949986 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1663. Min Range: -5.1663
Max Act: 4.8538. Min Act: -0.1700
Data Index: 8575141 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #19