Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3268 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.8685. Min Range: -2.8685
Max Act: 2.8685. Min Act: -0.1700
Data Index: 3912712 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8685. Min Range: -2.8685
Max Act: 2.8049. Min Act: -0.1700
Data Index: 3866727 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8685. Min Range: -2.8685
Max Act: 2.8208. Min Act: -0.1700
Data Index: 5196400 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8685. Min Range: -2.8685
Max Act: 2.7730. Min Act: -0.1700
Data Index: 6368213 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8685. Min Range: -2.8685
Max Act: 2.7411. Min Act: -0.1700
Data Index: 8473136 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8685. Min Range: -2.8685
Max Act: 2.7571. Min Act: -0.1700
Data Index: 5792695 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8685. Min Range: -2.8685
Max Act: 2.7411. Min Act: -0.1700
Data Index: 6499647 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8685. Min Range: -2.8685
Max Act: 2.7730. Min Act: -0.1700
Data Index: 7604873 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8685. Min Range: -2.8685
Max Act: 2.7411. Min Act: -0.1700
Data Index: 5475327 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8685. Min Range: -2.8685
Max Act: 2.7092. Min Act: -0.1700
Data Index: 5440644 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8685. Min Range: -2.8685
Max Act: 2.7252. Min Act: -0.1700
Data Index: 3001937 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8685. Min Range: -2.8685
Max Act: 2.7411. Min Act: -0.1700
Data Index: 4268059 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8685. Min Range: -2.8685
Max Act: 2.7411. Min Act: -0.1700
Data Index: 722841 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8685. Min Range: -2.8685
Max Act: 2.6932. Min Act: -0.1700
Data Index: 1576683 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8685. Min Range: -2.8685
Max Act: 2.6932. Min Act: -0.1700
Data Index: 2094634 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8685. Min Range: -2.8685
Max Act: 2.6932. Min Act: -0.1700
Data Index: 3647333 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8685. Min Range: -2.8685
Max Act: 2.6932. Min Act: -0.1700
Data Index: 671900 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8685. Min Range: -2.8685
Max Act: 2.6932. Min Act: -0.1700
Data Index: 6407102 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8685. Min Range: -2.8685
Max Act: 2.7092. Min Act: -0.1700
Data Index: 2268897 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8685. Min Range: -2.8685
Max Act: 2.6932. Min Act: -0.1700
Data Index: 417910 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #19