Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 446 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9495. Min Range: -4.9495
Max Act: 4.9495. Min Act: -0.1700
Data Index: 5513786 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9495. Min Range: -4.9495
Max Act: 4.9495. Min Act: -0.1700
Data Index: 4502500 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9495. Min Range: -4.9495
Max Act: 4.9182. Min Act: -0.1700
Data Index: 3742095 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9495. Min Range: -4.9495
Max Act: 4.9495. Min Act: -0.1700
Data Index: 2042990 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9495. Min Range: -4.9495
Max Act: 4.9182. Min Act: -0.1700
Data Index: 177290 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9495. Min Range: -4.9495
Max Act: 4.8870. Min Act: -0.1700
Data Index: 155930 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9495. Min Range: -4.9495
Max Act: 4.8870. Min Act: -0.1700
Data Index: 4069838 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9495. Min Range: -4.9495
Max Act: 4.8557. Min Act: -0.1700
Data Index: 8541333 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9495. Min Range: -4.9495
Max Act: 4.8557. Min Act: -0.1700
Data Index: 2817093 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9495. Min Range: -4.9495
Max Act: 4.8557. Min Act: -0.1700
Data Index: 761994 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9495. Min Range: -4.9495
Max Act: 4.8245. Min Act: -0.1700
Data Index: 1691486 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9495. Min Range: -4.9495
Max Act: 4.7932. Min Act: -0.1700
Data Index: 4786063 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9495. Min Range: -4.9495
Max Act: 4.7932. Min Act: -0.1700
Data Index: 4508381 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9495. Min Range: -4.9495
Max Act: 4.7620. Min Act: -0.1700
Data Index: 929531 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9495. Min Range: -4.9495
Max Act: 4.7620. Min Act: -0.1700
Data Index: 6268661 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9495. Min Range: -4.9495
Max Act: 4.7307. Min Act: -0.1700
Data Index: 5565891 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9495. Min Range: -4.9495
Max Act: 4.6995. Min Act: -0.1700
Data Index: 4995120 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9495. Min Range: -4.9495
Max Act: 4.6682. Min Act: -0.1700
Data Index: 5506297 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9495. Min Range: -4.9495
Max Act: 4.6995. Min Act: -0.1700
Data Index: 2727862 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9495. Min Range: -4.9495
Max Act: 4.6682. Min Act: -0.1700
Data Index: 8449890 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #19