Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2572 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0963. Min Range: -5.0963
Max Act: 5.0963. Min Act: -0.1700
Data Index: 89035 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0963. Min Range: -5.0963
Max Act: 4.9088. Min Act: -0.1700
Data Index: 7456150 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0963. Min Range: -5.0963
Max Act: 4.6901. Min Act: -0.1700
Data Index: 3053187 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0963. Min Range: -5.0963
Max Act: 4.5651. Min Act: -0.1700
Data Index: 8774042 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0963. Min Range: -5.0963
Max Act: 4.5651. Min Act: -0.1700
Data Index: 6748708 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0963. Min Range: -5.0963
Max Act: 4.5026. Min Act: -0.1700
Data Index: 3380032 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0963. Min Range: -5.0963
Max Act: 4.4713. Min Act: -0.1700
Data Index: 4524324 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0963. Min Range: -5.0963
Max Act: 4.4401. Min Act: -0.1700
Data Index: 2029917 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0963. Min Range: -5.0963
Max Act: 4.4088. Min Act: -0.1700
Data Index: 6465777 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0963. Min Range: -5.0963
Max Act: 4.4088. Min Act: -0.1700
Data Index: 4114882 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0963. Min Range: -5.0963
Max Act: 4.4088. Min Act: -0.1700
Data Index: 82219 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0963. Min Range: -5.0963
Max Act: 4.3776. Min Act: -0.1700
Data Index: 7076443 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0963. Min Range: -5.0963
Max Act: 4.3463. Min Act: -0.1700
Data Index: 1187229 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0963. Min Range: -5.0963
Max Act: 4.3463. Min Act: -0.1700
Data Index: 2721443 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0963. Min Range: -5.0963
Max Act: 4.3463. Min Act: -0.1700
Data Index: 3766470 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0963. Min Range: -5.0963
Max Act: 4.3776. Min Act: -0.1700
Data Index: 4620592 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0963. Min Range: -5.0963
Max Act: 4.3463. Min Act: -0.1700
Data Index: 1457452 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0963. Min Range: -5.0963
Max Act: 4.3151. Min Act: -0.1700
Data Index: 2696516 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0963. Min Range: -5.0963
Max Act: 4.3776. Min Act: -0.1700
Data Index: 3401729 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0963. Min Range: -5.0963
Max Act: 4.3151. Min Act: -0.1700
Data Index: 2156408 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #19