Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2821 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8455. Min Range: -5.8455
Max Act: 5.8455. Min Act: -0.1700
Data Index: 464260 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8455. Min Range: -5.8455
Max Act: 5.7518. Min Act: -0.1700
Data Index: 4238999 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8455. Min Range: -5.8455
Max Act: 5.5955. Min Act: -0.1700
Data Index: 3346787 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8455. Min Range: -5.8455
Max Act: 5.5330. Min Act: -0.1700
Data Index: 4113259 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8455. Min Range: -5.8455
Max Act: 5.5330. Min Act: -0.1700
Data Index: 7978100 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8455. Min Range: -5.8455
Max Act: 5.4393. Min Act: -0.1700
Data Index: 6518495 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8455. Min Range: -5.8455
Max Act: 5.4705. Min Act: -0.1700
Data Index: 5083513 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8455. Min Range: -5.8455
Max Act: 5.4393. Min Act: -0.1700
Data Index: 7549096 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8455. Min Range: -5.8455
Max Act: 5.3143. Min Act: -0.1700
Data Index: 8017781 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8455. Min Range: -5.8455
Max Act: 5.3455. Min Act: -0.1700
Data Index: 4286984 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8455. Min Range: -5.8455
Max Act: 5.3455. Min Act: -0.1700
Data Index: 4209088 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8455. Min Range: -5.8455
Max Act: 5.3143. Min Act: -0.1700
Data Index: 8556176 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8455. Min Range: -5.8455
Max Act: 5.3768. Min Act: -0.1700
Data Index: 1829233 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8455. Min Range: -5.8455
Max Act: 5.3455. Min Act: -0.1700
Data Index: 1748094 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8455. Min Range: -5.8455
Max Act: 5.3455. Min Act: -0.1700
Data Index: 6024675 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8455. Min Range: -5.8455
Max Act: 5.3455. Min Act: -0.1700
Data Index: 7254851 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8455. Min Range: -5.8455
Max Act: 5.2830. Min Act: -0.1700
Data Index: 6510083 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8455. Min Range: -5.8455
Max Act: 5.2830. Min Act: -0.1700
Data Index: 4169602 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8455. Min Range: -5.8455
Max Act: 5.2830. Min Act: -0.1700
Data Index: 2758690 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8455. Min Range: -5.8455
Max Act: 5.2830. Min Act: -0.1700
Data Index: 1553814 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #19