Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3807 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.0870. Min Range: -7.0870
Max Act: 7.0870. Min Act: -0.1700
Data Index: 994261 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0870. Min Range: -7.0870
Max Act: 6.9307. Min Act: -0.1700
Data Index: 8555320 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0870. Min Range: -7.0870
Max Act: 6.9307. Min Act: -0.1700
Data Index: 3576896 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0870. Min Range: -7.0870
Max Act: 6.8995. Min Act: -0.1700
Data Index: 3272958 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0870. Min Range: -7.0870
Max Act: 6.8995. Min Act: -0.1700
Data Index: 7236718 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0870. Min Range: -7.0870
Max Act: 6.8682. Min Act: -0.1700
Data Index: 1378737 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0870. Min Range: -7.0870
Max Act: 6.8682. Min Act: -0.1700
Data Index: 4826691 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0870. Min Range: -7.0870
Max Act: 6.8370. Min Act: -0.1700
Data Index: 8051264 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0870. Min Range: -7.0870
Max Act: 6.8682. Min Act: -0.1700
Data Index: 1255867 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0870. Min Range: -7.0870
Max Act: 6.8370. Min Act: -0.1700
Data Index: 774142 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0870. Min Range: -7.0870
Max Act: 6.8057. Min Act: -0.1700
Data Index: 5897666 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0870. Min Range: -7.0870
Max Act: 6.8057. Min Act: -0.1700
Data Index: 7438421 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0870. Min Range: -7.0870
Max Act: 6.7745. Min Act: -0.1700
Data Index: 4997127 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0870. Min Range: -7.0870
Max Act: 6.8057. Min Act: -0.1700
Data Index: 3543806 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0870. Min Range: -7.0870
Max Act: 6.7432. Min Act: -0.1700
Data Index: 1066084 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0870. Min Range: -7.0870
Max Act: 6.7745. Min Act: -0.1700
Data Index: 7475183 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0870. Min Range: -7.0870
Max Act: 6.7745. Min Act: -0.1700
Data Index: 4041947 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0870. Min Range: -7.0870
Max Act: 6.7745. Min Act: -0.1700
Data Index: 5854933 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0870. Min Range: -7.0870
Max Act: 6.7745. Min Act: -0.1700
Data Index: 6372939 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0870. Min Range: -7.0870
Max Act: 6.7432. Min Act: -0.1700
Data Index: 5611039 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #19