Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2632 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1882. Min Range: -5.1882
Max Act: 5.1882. Min Act: -0.1700
Data Index: 5229266 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1882. Min Range: -5.1882
Max Act: 5.0319. Min Act: -0.1700
Data Index: 4597695 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1882. Min Range: -5.1882
Max Act: 5.0319. Min Act: -0.1700
Data Index: 3931084 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1882. Min Range: -5.1882
Max Act: 5.0007. Min Act: -0.1700
Data Index: 3507035 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1882. Min Range: -5.1882
Max Act: 5.0007. Min Act: -0.1700
Data Index: 4552784 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1882. Min Range: -5.1882
Max Act: 4.9382. Min Act: -0.1700
Data Index: 7122229 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1882. Min Range: -5.1882
Max Act: 4.9694. Min Act: -0.1700
Data Index: 4179120 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1882. Min Range: -5.1882
Max Act: 4.9382. Min Act: -0.1700
Data Index: 3195109 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1882. Min Range: -5.1882
Max Act: 4.9382. Min Act: -0.1700
Data Index: 2000160 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1882. Min Range: -5.1882
Max Act: 4.9382. Min Act: -0.1700
Data Index: 2769053 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1882. Min Range: -5.1882
Max Act: 4.9382. Min Act: -0.1700
Data Index: 1182699 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1882. Min Range: -5.1882
Max Act: 4.9069. Min Act: -0.1700
Data Index: 7239511 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1882. Min Range: -5.1882
Max Act: 4.9694. Min Act: -0.1700
Data Index: 4864975 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1882. Min Range: -5.1882
Max Act: 4.8757. Min Act: -0.1700
Data Index: 1400676 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1882. Min Range: -5.1882
Max Act: 4.8757. Min Act: -0.1700
Data Index: 1608802 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1882. Min Range: -5.1882
Max Act: 4.8757. Min Act: -0.1700
Data Index: 7317060 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1882. Min Range: -5.1882
Max Act: 4.8757. Min Act: -0.1700
Data Index: 5480769 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1882. Min Range: -5.1882
Max Act: 4.8757. Min Act: -0.1700
Data Index: 4097213 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1882. Min Range: -5.1882
Max Act: 4.9069. Min Act: -0.1700
Data Index: 576384 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1882. Min Range: -5.1882
Max Act: 4.8757. Min Act: -0.1700
Data Index: 1827734 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #19