Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 975 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.4512. Min Range: -2.4512
Max Act: 2.4349. Min Act: -0.1700
Data Index: 950852 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4512. Min Range: -2.4512
Max Act: 2.4186. Min Act: -0.1700
Data Index: 7814689 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4512. Min Range: -2.4512
Max Act: 2.4512. Min Act: -0.1700
Data Index: 1920027 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4512. Min Range: -2.4512
Max Act: 2.4186. Min Act: -0.1700
Data Index: 6331143 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4512. Min Range: -2.4512
Max Act: 2.3860. Min Act: -0.1700
Data Index: 805411 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4512. Min Range: -2.4512
Max Act: 2.4023. Min Act: -0.1700
Data Index: 8345199 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4512. Min Range: -2.4512
Max Act: 2.4186. Min Act: -0.1700
Data Index: 6473431 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4512. Min Range: -2.4512
Max Act: 2.4023. Min Act: -0.1700
Data Index: 3682866 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4512. Min Range: -2.4512
Max Act: 2.3860. Min Act: -0.1700
Data Index: 2132957 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4512. Min Range: -2.4512
Max Act: 2.3860. Min Act: -0.1700
Data Index: 6398037 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4512. Min Range: -2.4512
Max Act: 2.3533. Min Act: -0.1700
Data Index: 8018636 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4512. Min Range: -2.4512
Max Act: 2.3533. Min Act: -0.1700
Data Index: 2749827 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4512. Min Range: -2.4512
Max Act: 2.3696. Min Act: -0.1700
Data Index: 4751105 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4512. Min Range: -2.4512
Max Act: 2.3533. Min Act: -0.1700
Data Index: 6641988 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4512. Min Range: -2.4512
Max Act: 2.3369. Min Act: -0.1700
Data Index: 5190632 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4512. Min Range: -2.4512
Max Act: 2.3533. Min Act: -0.1700
Data Index: 912432 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4512. Min Range: -2.4512
Max Act: 2.3369. Min Act: -0.1700
Data Index: 8566711 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4512. Min Range: -2.4512
Max Act: 2.3369. Min Act: -0.1700
Data Index: 8557607 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4512. Min Range: -2.4512
Max Act: 2.3369. Min Act: -0.1700
Data Index: 405058 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4512. Min Range: -2.4512
Max Act: 2.3369. Min Act: -0.1700
Data Index: 8001884 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #19