Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 896 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7166. Min Range: -6.7166
Max Act: 6.7166. Min Act: -0.1700
Data Index: 6073064 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7166. Min Range: -6.7166
Max Act: 6.5603. Min Act: -0.1700
Data Index: 5467913 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7166. Min Range: -6.7166
Max Act: 6.5291. Min Act: -0.1700
Data Index: 288176 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7166. Min Range: -6.7166
Max Act: 6.4353. Min Act: -0.1700
Data Index: 8678402 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7166. Min Range: -6.7166
Max Act: 6.4353. Min Act: -0.1700
Data Index: 5296291 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7166. Min Range: -6.7166
Max Act: 6.4041. Min Act: -0.1700
Data Index: 3587871 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7166. Min Range: -6.7166
Max Act: 6.3728. Min Act: -0.1700
Data Index: 878039 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7166. Min Range: -6.7166
Max Act: 6.3416. Min Act: -0.1700
Data Index: 8555522 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7166. Min Range: -6.7166
Max Act: 6.2791. Min Act: -0.1698
Data Index: 2529079 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7166. Min Range: -6.7166
Max Act: 6.2791. Min Act: -0.1700
Data Index: 599632 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7166. Min Range: -6.7166
Max Act: 6.3103. Min Act: -0.1700
Data Index: 367990 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7166. Min Range: -6.7166
Max Act: 6.2791. Min Act: -0.1698
Data Index: 5296290 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7166. Min Range: -6.7166
Max Act: 6.2791. Min Act: -0.1700
Data Index: 938836 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7166. Min Range: -6.7166
Max Act: 6.2791. Min Act: -0.1700
Data Index: 4863752 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7166. Min Range: -6.7166
Max Act: 6.2791. Min Act: -0.1700
Data Index: 539460 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7166. Min Range: -6.7166
Max Act: 6.2791. Min Act: -0.1700
Data Index: 2702798 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7166. Min Range: -6.7166
Max Act: 6.2478. Min Act: -0.1700
Data Index: 2069429 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7166. Min Range: -6.7166
Max Act: 6.2478. Min Act: -0.1700
Data Index: 6601575 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7166. Min Range: -6.7166
Max Act: 6.2478. Min Act: -0.1700
Data Index: 3474279 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7166. Min Range: -6.7166
Max Act: 6.2791. Min Act: -0.1700
Data Index: 8555523 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #19