Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3256 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.7012. Min Range: -7.7012
Max Act: 7.7012. Min Act: -0.1700
Data Index: 1314964 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7012. Min Range: -7.7012
Max Act: 7.5449. Min Act: -0.1700
Data Index: 5556482 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7012. Min Range: -7.7012
Max Act: 7.5449. Min Act: -0.1700
Data Index: 5937091 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7012. Min Range: -7.7012
Max Act: 7.5137. Min Act: -0.1700
Data Index: 2242874 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7012. Min Range: -7.7012
Max Act: 7.3887. Min Act: -0.1700
Data Index: 915541 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7012. Min Range: -7.7012
Max Act: 7.3887. Min Act: -0.1700
Data Index: 3663974 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7012. Min Range: -7.7012
Max Act: 7.3262. Min Act: -0.1700
Data Index: 4158945 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7012. Min Range: -7.7012
Max Act: 7.3574. Min Act: -0.1700
Data Index: 4113360 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7012. Min Range: -7.7012
Max Act: 7.3262. Min Act: -0.1700
Data Index: 563375 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7012. Min Range: -7.7012
Max Act: 7.2012. Min Act: -0.1700
Data Index: 4259569 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7012. Min Range: -7.7012
Max Act: 7.2012. Min Act: -0.1700
Data Index: 3669593 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7012. Min Range: -7.7012
Max Act: 7.1699. Min Act: -0.1700
Data Index: 7096963 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7012. Min Range: -7.7012
Max Act: 7.0762. Min Act: -0.1700
Data Index: 2843577 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7012. Min Range: -7.7012
Max Act: 7.1074. Min Act: -0.1700
Data Index: 563374 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7012. Min Range: -7.7012
Max Act: 7.0762. Min Act: -0.1700
Data Index: 556852 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7012. Min Range: -7.7012
Max Act: 7.0762. Min Act: -0.1700
Data Index: 3841242 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7012. Min Range: -7.7012
Max Act: 7.0449. Min Act: -0.1700
Data Index: 57312 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7012. Min Range: -7.7012
Max Act: 7.0449. Min Act: -0.1700
Data Index: 2367682 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7012. Min Range: -7.7012
Max Act: 7.0449. Min Act: -0.1700
Data Index: 2166907 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7012. Min Range: -7.7012
Max Act: 7.0137. Min Act: -0.1700
Data Index: 5401429 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #19