Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2382 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3887. Min Range: -3.3887
Max Act: 3.3887. Min Act: -0.1700
Data Index: 6299941 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3887. Min Range: -3.3887
Max Act: 3.3574. Min Act: -0.1700
Data Index: 2119846 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3887. Min Range: -3.3887
Max Act: 3.3417. Min Act: -0.1700
Data Index: 1822784 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3887. Min Range: -3.3887
Max Act: 3.3260. Min Act: -0.1700
Data Index: 2191051 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3887. Min Range: -3.3887
Max Act: 3.2946. Min Act: -0.1700
Data Index: 7831274 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3887. Min Range: -3.3887
Max Act: 3.3103. Min Act: -0.1700
Data Index: 316336 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3887. Min Range: -3.3887
Max Act: 3.2946. Min Act: -0.1700
Data Index: 3770058 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3887. Min Range: -3.3887
Max Act: 3.3417. Min Act: -0.1700
Data Index: 4073983 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3887. Min Range: -3.3887
Max Act: 3.2946. Min Act: -0.1700
Data Index: 1702760 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3887. Min Range: -3.3887
Max Act: 3.2946. Min Act: -0.1700
Data Index: 5082583 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3887. Min Range: -3.3887
Max Act: 3.2946. Min Act: -0.1700
Data Index: 3569621 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3887. Min Range: -3.3887
Max Act: 3.2946. Min Act: -0.1700
Data Index: 6544091 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3887. Min Range: -3.3887
Max Act: 3.2789. Min Act: -0.1700
Data Index: 870131 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3887. Min Range: -3.3887
Max Act: 3.2946. Min Act: -0.1700
Data Index: 5802711 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3887. Min Range: -3.3887
Max Act: 3.2632. Min Act: -0.1700
Data Index: 2191050 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3887. Min Range: -3.3887
Max Act: 3.2946. Min Act: -0.1700
Data Index: 56710 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3887. Min Range: -3.3887
Max Act: 3.2789. Min Act: -0.1700
Data Index: 4445300 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3887. Min Range: -3.3887
Max Act: 3.2946. Min Act: -0.1700
Data Index: 5955738 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3887. Min Range: -3.3887
Max Act: 3.2946. Min Act: -0.1700
Data Index: 1166918 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3887. Min Range: -3.3887
Max Act: 3.2632. Min Act: -0.1700
Data Index: 3831580 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #19