Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1206 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8034. Min Range: -5.8034
Max Act: 5.8034. Min Act: -0.1700
Data Index: 7071582 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8034. Min Range: -5.8034
Max Act: 5.7409. Min Act: -0.1700
Data Index: 1381254 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8034. Min Range: -5.8034
Max Act: 5.7409. Min Act: -0.1700
Data Index: 990602 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8034. Min Range: -5.8034
Max Act: 5.7409. Min Act: -0.1700
Data Index: 3724682 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8034. Min Range: -5.8034
Max Act: 5.5534. Min Act: -0.1700
Data Index: 2306338 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8034. Min Range: -5.8034
Max Act: 5.4596. Min Act: -0.1700
Data Index: 2462726 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8034. Min Range: -5.8034
Max Act: 5.4284. Min Act: -0.1700
Data Index: 2527064 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8034. Min Range: -5.8034
Max Act: 5.3659. Min Act: -0.1700
Data Index: 5536968 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8034. Min Range: -5.8034
Max Act: 5.3659. Min Act: -0.1700
Data Index: 3645083 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8034. Min Range: -5.8034
Max Act: 5.3034. Min Act: -0.1700
Data Index: 6517385 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8034. Min Range: -5.8034
Max Act: 5.3346. Min Act: -0.1700
Data Index: 7630175 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8034. Min Range: -5.8034
Max Act: 5.2096. Min Act: -0.1700
Data Index: 8399876 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8034. Min Range: -5.8034
Max Act: 5.3034. Min Act: -0.1700
Data Index: 4094060 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8034. Min Range: -5.8034
Max Act: 5.2721. Min Act: -0.1700
Data Index: 4626005 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8034. Min Range: -5.8034
Max Act: 5.2721. Min Act: -0.1700
Data Index: 6868607 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8034. Min Range: -5.8034
Max Act: 5.2721. Min Act: -0.1700
Data Index: 1176460 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8034. Min Range: -5.8034
Max Act: 5.1784. Min Act: -0.1700
Data Index: 1177601 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8034. Min Range: -5.8034
Max Act: 5.1784. Min Act: -0.1700
Data Index: 8453853 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8034. Min Range: -5.8034
Max Act: 5.1784. Min Act: -0.1700
Data Index: 8089507 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8034. Min Range: -5.8034
Max Act: 5.1784. Min Act: -0.1700
Data Index: 1062215 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #19