Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 51 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2073. Min Range: -3.2073
Max Act: 3.2073. Min Act: -0.1700
Data Index: 444918 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2073. Min Range: -3.2073
Max Act: 3.1758. Min Act: -0.1700
Data Index: 674642 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2073. Min Range: -3.2073
Max Act: 3.2073. Min Act: -0.1700
Data Index: 7470035 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2073. Min Range: -3.2073
Max Act: 3.1916. Min Act: -0.1700
Data Index: 3113539 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2073. Min Range: -3.2073
Max Act: 3.1443. Min Act: -0.1700
Data Index: 8590185 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2073. Min Range: -3.2073
Max Act: 3.1286. Min Act: -0.1700
Data Index: 988614 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2073. Min Range: -3.2073
Max Act: 3.1443. Min Act: -0.1700
Data Index: 2607105 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2073. Min Range: -3.2073
Max Act: 3.1286. Min Act: -0.1700
Data Index: 7092035 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2073. Min Range: -3.2073
Max Act: 3.1443. Min Act: -0.1700
Data Index: 3715542 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2073. Min Range: -3.2073
Max Act: 3.1601. Min Act: -0.1700
Data Index: 3774218 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2073. Min Range: -3.2073
Max Act: 3.1286. Min Act: -0.1700
Data Index: 4982537 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2073. Min Range: -3.2073
Max Act: 3.1286. Min Act: -0.1700
Data Index: 51879 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2073. Min Range: -3.2073
Max Act: 3.1128. Min Act: -0.1700
Data Index: 7317916 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2073. Min Range: -3.2073
Max Act: 3.1128. Min Act: -0.1700
Data Index: 5687911 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2073. Min Range: -3.2073
Max Act: 3.1128. Min Act: -0.1700
Data Index: 5803818 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2073. Min Range: -3.2073
Max Act: 3.0971. Min Act: -0.1700
Data Index: 6307546 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2073. Min Range: -3.2073
Max Act: 3.0971. Min Act: -0.1700
Data Index: 4529642 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2073. Min Range: -3.2073
Max Act: 3.0813. Min Act: -0.1700
Data Index: 1275039 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2073. Min Range: -3.2073
Max Act: 3.0971. Min Act: -0.1700
Data Index: 6009707 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2073. Min Range: -3.2073
Max Act: 3.0971. Min Act: -0.1700
Data Index: 8372791 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #19