Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 37 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0151. Min Range: -3.0151
Max Act: 3.0151. Min Act: -0.1700
Data Index: 5122315 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0151. Min Range: -3.0151
Max Act: 2.9835. Min Act: -0.1700
Data Index: 8437931 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0151. Min Range: -3.0151
Max Act: 2.9676. Min Act: -0.1700
Data Index: 4045467 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0151. Min Range: -3.0151
Max Act: 2.9676. Min Act: -0.1700
Data Index: 424449 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0151. Min Range: -3.0151
Max Act: 2.9360. Min Act: -0.1700
Data Index: 3293580 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0151. Min Range: -3.0151
Max Act: 2.9201. Min Act: -0.1700
Data Index: 6141122 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0151. Min Range: -3.0151
Max Act: 2.9043. Min Act: -0.1700
Data Index: 3205521 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0151. Min Range: -3.0151
Max Act: 2.8408. Min Act: -0.1700
Data Index: 7266399 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0151. Min Range: -3.0151
Max Act: 2.8408. Min Act: -0.1700
Data Index: 4270654 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0151. Min Range: -3.0151
Max Act: 2.8567. Min Act: -0.1700
Data Index: 2926772 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0151. Min Range: -3.0151
Max Act: 2.8408. Min Act: -0.1700
Data Index: 3170048 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0151. Min Range: -3.0151
Max Act: 2.8090. Min Act: -0.1700
Data Index: 3260774 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0151. Min Range: -3.0151
Max Act: 2.8090. Min Act: -0.1700
Data Index: 314016 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0151. Min Range: -3.0151
Max Act: 2.8249. Min Act: -0.1700
Data Index: 4355708 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0151. Min Range: -3.0151
Max Act: 2.8567. Min Act: -0.1700
Data Index: 7552236 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0151. Min Range: -3.0151
Max Act: 2.7930. Min Act: -0.1700
Data Index: 6305898 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0151. Min Range: -3.0151
Max Act: 2.7930. Min Act: -0.1700
Data Index: 7705951 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0151. Min Range: -3.0151
Max Act: 2.7930. Min Act: -0.1700
Data Index: 6236156 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0151. Min Range: -3.0151
Max Act: 2.7612. Min Act: -0.1700
Data Index: 4119300 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0151. Min Range: -3.0151
Max Act: 2.7771. Min Act: -0.1700
Data Index: 2677984 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #19