Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 473 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4190. Min Range: -4.4190
Max Act: 4.4190. Min Act: -0.1700
Data Index: 1516592 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4190. Min Range: -4.4190
Max Act: 4.2627. Min Act: -0.1700
Data Index: 4677367 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4190. Min Range: -4.4190
Max Act: 4.2627. Min Act: -0.1700
Data Index: 8440072 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4190. Min Range: -4.4190
Max Act: 4.2627. Min Act: -0.1700
Data Index: 1999641 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4190. Min Range: -4.4190
Max Act: 4.1689. Min Act: -0.1700
Data Index: 6384194 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4190. Min Range: -4.4190
Max Act: 4.0752. Min Act: -0.1700
Data Index: 2331241 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4190. Min Range: -4.4190
Max Act: 4.0752. Min Act: -0.1700
Data Index: 5780268 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4190. Min Range: -4.4190
Max Act: 4.0752. Min Act: -0.1700
Data Index: 643753 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4190. Min Range: -4.4190
Max Act: 4.0752. Min Act: -0.1700
Data Index: 4558695 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4190. Min Range: -4.4190
Max Act: 4.0752. Min Act: -0.1700
Data Index: 8432392 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4190. Min Range: -4.4190
Max Act: 4.0752. Min Act: -0.1700
Data Index: 6735221 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4190. Min Range: -4.4190
Max Act: 4.0752. Min Act: -0.1700
Data Index: 4137708 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4190. Min Range: -4.4190
Max Act: 4.0439. Min Act: -0.1700
Data Index: 59216 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4190. Min Range: -4.4190
Max Act: 4.0127. Min Act: -0.1700
Data Index: 8656757 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4190. Min Range: -4.4190
Max Act: 4.0127. Min Act: -0.1700
Data Index: 3000903 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4190. Min Range: -4.4190
Max Act: 3.9814. Min Act: -0.1700
Data Index: 2496253 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4190. Min Range: -4.4190
Max Act: 3.9814. Min Act: -0.1700
Data Index: 4071881 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4190. Min Range: -4.4190
Max Act: 3.9814. Min Act: -0.1700
Data Index: 3681117 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4190. Min Range: -4.4190
Max Act: 3.9814. Min Act: -0.1700
Data Index: 5034911 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4190. Min Range: -4.4190
Max Act: 3.9814. Min Act: -0.1700
Data Index: 3192583 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #19