Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3895 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.3455. Min Range: -2.3455
Max Act: 2.3455. Min Act: -0.1700
Data Index: 5964045 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3455. Min Range: -2.3455
Max Act: 2.2963. Min Act: -0.1700
Data Index: 8583119 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3455. Min Range: -2.3455
Max Act: 2.2633. Min Act: -0.1700
Data Index: 7961381 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3455. Min Range: -2.3455
Max Act: 2.1971. Min Act: -0.1700
Data Index: 1782529 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3455. Min Range: -2.3455
Max Act: 2.2303. Min Act: -0.1700
Data Index: 7449827 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3455. Min Range: -2.3455
Max Act: 2.2303. Min Act: -0.1700
Data Index: 1013165 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3455. Min Range: -2.3455
Max Act: 2.2303. Min Act: -0.1700
Data Index: 4030492 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3455. Min Range: -2.3455
Max Act: 2.2137. Min Act: -0.1700
Data Index: 5633087 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3455. Min Range: -2.3455
Max Act: 2.2137. Min Act: -0.1700
Data Index: 7983634 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3455. Min Range: -2.3455
Max Act: 2.2303. Min Act: -0.1700
Data Index: 5271076 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3455. Min Range: -2.3455
Max Act: 2.2137. Min Act: -0.1700
Data Index: 858988 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3455. Min Range: -2.3455
Max Act: 2.1639. Min Act: -0.1700
Data Index: 1426164 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3455. Min Range: -2.3455
Max Act: 2.1971. Min Act: -0.1700
Data Index: 6060996 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3455. Min Range: -2.3455
Max Act: 2.1805. Min Act: -0.1700
Data Index: 808025 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3455. Min Range: -2.3455
Max Act: 2.1805. Min Act: -0.1700
Data Index: 242341 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3455. Min Range: -2.3455
Max Act: 2.1971. Min Act: -0.1700
Data Index: 5561427 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3455. Min Range: -2.3455
Max Act: 2.1971. Min Act: -0.1700
Data Index: 6507607 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3455. Min Range: -2.3455
Max Act: 2.1805. Min Act: -0.1700
Data Index: 948542 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3455. Min Range: -2.3455
Max Act: 2.1472. Min Act: -0.1700
Data Index: 862879 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3455. Min Range: -2.3455
Max Act: 2.2137. Min Act: -0.1700
Data Index: 4469206 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #19