Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2900 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8970. Min Range: -5.8970
Max Act: 5.8970. Min Act: -0.1700
Data Index: 5004644 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8970. Min Range: -5.8970
Max Act: 5.8657. Min Act: -0.1700
Data Index: 4612201 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8970. Min Range: -5.8970
Max Act: 5.8345. Min Act: -0.1700
Data Index: 5072753 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8970. Min Range: -5.8970
Max Act: 5.8032. Min Act: -0.1700
Data Index: 3890395 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8970. Min Range: -5.8970
Max Act: 5.7407. Min Act: -0.1700
Data Index: 6619057 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8970. Min Range: -5.8970
Max Act: 5.7095. Min Act: -0.1700
Data Index: 4990085 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8970. Min Range: -5.8970
Max Act: 5.6782. Min Act: -0.1700
Data Index: 2545441 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8970. Min Range: -5.8970
Max Act: 5.6470. Min Act: -0.1700
Data Index: 1481649 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8970. Min Range: -5.8970
Max Act: 5.6157. Min Act: -0.1700
Data Index: 1103628 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8970. Min Range: -5.8970
Max Act: 5.6157. Min Act: -0.1700
Data Index: 3023589 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8970. Min Range: -5.8970
Max Act: 5.6157. Min Act: -0.1700
Data Index: 7821396 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8970. Min Range: -5.8970
Max Act: 5.5532. Min Act: -0.1700
Data Index: 5451927 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8970. Min Range: -5.8970
Max Act: 5.5220. Min Act: -0.1700
Data Index: 7368861 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8970. Min Range: -5.8970
Max Act: 5.5220. Min Act: -0.1700
Data Index: 8493552 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8970. Min Range: -5.8970
Max Act: 5.5220. Min Act: -0.1700
Data Index: 8670227 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8970. Min Range: -5.8970
Max Act: 5.5220. Min Act: -0.1700
Data Index: 1196992 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8970. Min Range: -5.8970
Max Act: 5.4907. Min Act: -0.1700
Data Index: 72159 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8970. Min Range: -5.8970
Max Act: 5.4907. Min Act: -0.1700
Data Index: 3012984 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8970. Min Range: -5.8970
Max Act: 5.4595. Min Act: -0.1700
Data Index: 1869228 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8970. Min Range: -5.8970
Max Act: 5.4595. Min Act: -0.1700
Data Index: 5162274 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #19