Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3688 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.6109. Min Range: -2.6109
Max Act: 2.6109. Min Act: -0.1700
Data Index: 1432730 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6109. Min Range: -2.6109
Max Act: 2.5464. Min Act: -0.1700
Data Index: 1293059 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6109. Min Range: -2.6109
Max Act: 2.5141. Min Act: -0.1700
Data Index: 903048 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6109. Min Range: -2.6109
Max Act: 2.4492. Min Act: -0.1700
Data Index: 2847615 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6109. Min Range: -2.6109
Max Act: 2.4329. Min Act: -0.1700
Data Index: 8116640 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6109. Min Range: -2.6109
Max Act: 2.4329. Min Act: -0.1700
Data Index: 6771737 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6109. Min Range: -2.6109
Max Act: 2.4329. Min Act: -0.1700
Data Index: 2973765 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6109. Min Range: -2.6109
Max Act: 2.4167. Min Act: -0.1700
Data Index: 7076332 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6109. Min Range: -2.6109
Max Act: 2.4167. Min Act: -0.1700
Data Index: 3572653 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6109. Min Range: -2.6109
Max Act: 2.4004. Min Act: -0.1700
Data Index: 2252065 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6109. Min Range: -2.6109
Max Act: 2.3840. Min Act: -0.1700
Data Index: 4378504 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6109. Min Range: -2.6109
Max Act: 2.3513. Min Act: -0.1700
Data Index: 3515496 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6109. Min Range: -2.6109
Max Act: 2.3349. Min Act: -0.1700
Data Index: 6234143 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6109. Min Range: -2.6109
Max Act: 2.3349. Min Act: -0.1700
Data Index: 2541848 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6109. Min Range: -2.6109
Max Act: 2.3020. Min Act: -0.1700
Data Index: 7970540 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6109. Min Range: -2.6109
Max Act: 2.3020. Min Act: -0.1700
Data Index: 2418349 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6109. Min Range: -2.6109
Max Act: 2.3513. Min Act: -0.1700
Data Index: 4261248 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6109. Min Range: -2.6109
Max Act: 2.2856. Min Act: -0.1700
Data Index: 5042406 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6109. Min Range: -2.6109
Max Act: 2.3185. Min Act: -0.1700
Data Index: 2416850 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6109. Min Range: -2.6109
Max Act: 2.3020. Min Act: -0.1700
Data Index: 891335 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #19