Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2904 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1103. Min Range: -7.1103
Max Act: 7.1103. Min Act: -0.1700
Data Index: 5557502 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1103. Min Range: -7.1103
Max Act: 6.9853. Min Act: -0.1700
Data Index: 6983589 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1103. Min Range: -7.1103
Max Act: 6.8603. Min Act: -0.1700
Data Index: 3558789 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1103. Min Range: -7.1103
Max Act: 6.8603. Min Act: -0.1700
Data Index: 685316 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1103. Min Range: -7.1103
Max Act: 6.8603. Min Act: -0.1700
Data Index: 2260159 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1103. Min Range: -7.1103
Max Act: 6.8603. Min Act: -0.1700
Data Index: 4043460 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1103. Min Range: -7.1103
Max Act: 6.7978. Min Act: -0.1700
Data Index: 6307207 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1103. Min Range: -7.1103
Max Act: 6.8290. Min Act: -0.1700
Data Index: 8026320 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1103. Min Range: -7.1103
Max Act: 6.7978. Min Act: -0.1700
Data Index: 1900564 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1103. Min Range: -7.1103
Max Act: 6.7978. Min Act: -0.1700
Data Index: 5477544 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1103. Min Range: -7.1103
Max Act: 6.7665. Min Act: -0.1700
Data Index: 5969582 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1103. Min Range: -7.1103
Max Act: 6.7353. Min Act: -0.1700
Data Index: 6186788 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1103. Min Range: -7.1103
Max Act: 6.7353. Min Act: -0.1700
Data Index: 6751274 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1103. Min Range: -7.1103
Max Act: 6.7353. Min Act: -0.1700
Data Index: 8468255 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1103. Min Range: -7.1103
Max Act: 6.7040. Min Act: -0.1700
Data Index: 1141890 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1103. Min Range: -7.1103
Max Act: 6.7040. Min Act: -0.1700
Data Index: 988951 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1103. Min Range: -7.1103
Max Act: 6.7040. Min Act: -0.1700
Data Index: 3058969 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1103. Min Range: -7.1103
Max Act: 6.7040. Min Act: -0.1700
Data Index: 4745097 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1103. Min Range: -7.1103
Max Act: 6.6728. Min Act: -0.1700
Data Index: 8090841 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1103. Min Range: -7.1103
Max Act: 6.6728. Min Act: -0.1700
Data Index: 5036973 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #19