Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3625 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4618. Min Range: -6.4618
Max Act: 6.4618. Min Act: -0.1700
Data Index: 4037980 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4618. Min Range: -6.4618
Max Act: 6.4306. Min Act: -0.1700
Data Index: 7085302 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4618. Min Range: -6.4618
Max Act: 6.3056. Min Act: -0.1700
Data Index: 7002880 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4618. Min Range: -6.4618
Max Act: 6.3056. Min Act: -0.1700
Data Index: 6748173 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4618. Min Range: -6.4618
Max Act: 6.3056. Min Act: -0.1700
Data Index: 8487047 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4618. Min Range: -6.4618
Max Act: 6.2431. Min Act: -0.1700
Data Index: 8538719 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4618. Min Range: -6.4618
Max Act: 6.2431. Min Act: -0.1700
Data Index: 8033347 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4618. Min Range: -6.4618
Max Act: 6.2118. Min Act: -0.1700
Data Index: 1151454 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4618. Min Range: -6.4618
Max Act: 6.1806. Min Act: -0.1700
Data Index: 4633285 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4618. Min Range: -6.4618
Max Act: 6.1493. Min Act: -0.1700
Data Index: 3140311 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4618. Min Range: -6.4618
Max Act: 6.1493. Min Act: -0.1700
Data Index: 4039907 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4618. Min Range: -6.4618
Max Act: 6.1493. Min Act: -0.1700
Data Index: 7081902 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4618. Min Range: -6.4618
Max Act: 6.1806. Min Act: -0.1700
Data Index: 5787680 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4618. Min Range: -6.4618
Max Act: 6.1493. Min Act: -0.1700
Data Index: 4368025 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4618. Min Range: -6.4618
Max Act: 6.1181. Min Act: -0.1700
Data Index: 2770279 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4618. Min Range: -6.4618
Max Act: 6.1181. Min Act: -0.1700
Data Index: 2526942 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4618. Min Range: -6.4618
Max Act: 6.1181. Min Act: -0.1700
Data Index: 4131911 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4618. Min Range: -6.4618
Max Act: 6.0868. Min Act: -0.1700
Data Index: 5074063 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4618. Min Range: -6.4618
Max Act: 6.0868. Min Act: -0.1700
Data Index: 1703211 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4618. Min Range: -6.4618
Max Act: 6.0556. Min Act: -0.1700
Data Index: 2838779 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #19