Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2845 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.0536. Min Range: -7.0536
Max Act: 7.0536. Min Act: -0.1700
Data Index: 5481846 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0536. Min Range: -7.0536
Max Act: 6.8348. Min Act: -0.1700
Data Index: 3400859 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0536. Min Range: -7.0536
Max Act: 6.7723. Min Act: -0.1700
Data Index: 3007482 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0536. Min Range: -7.0536
Max Act: 6.7723. Min Act: -0.1700
Data Index: 760729 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0536. Min Range: -7.0536
Max Act: 6.7411. Min Act: -0.1700
Data Index: 5916586 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0536. Min Range: -7.0536
Max Act: 6.5848. Min Act: -0.1700
Data Index: 6357929 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0536. Min Range: -7.0536
Max Act: 6.5223. Min Act: -0.1700
Data Index: 4298834 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0536. Min Range: -7.0536
Max Act: 6.5536. Min Act: -0.1700
Data Index: 8815670 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0536. Min Range: -7.0536
Max Act: 6.5223. Min Act: -0.1700
Data Index: 8776367 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0536. Min Range: -7.0536
Max Act: 6.5223. Min Act: -0.1700
Data Index: 8456612 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0536. Min Range: -7.0536
Max Act: 6.4911. Min Act: -0.1700
Data Index: 6524992 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0536. Min Range: -7.0536
Max Act: 6.4911. Min Act: -0.1700
Data Index: 8368575 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0536. Min Range: -7.0536
Max Act: 6.4598. Min Act: -0.1700
Data Index: 2812613 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0536. Min Range: -7.0536
Max Act: 6.4598. Min Act: -0.1700
Data Index: 1899511 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0536. Min Range: -7.0536
Max Act: 6.4286. Min Act: -0.1700
Data Index: 828468 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0536. Min Range: -7.0536
Max Act: 6.4286. Min Act: -0.1700
Data Index: 2563768 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0536. Min Range: -7.0536
Max Act: 6.3973. Min Act: -0.1700
Data Index: 6797273 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0536. Min Range: -7.0536
Max Act: 6.3973. Min Act: -0.1700
Data Index: 6016102 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0536. Min Range: -7.0536
Max Act: 6.3661. Min Act: -0.1700
Data Index: 299625 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0536. Min Range: -7.0536
Max Act: 6.3973. Min Act: -0.1700
Data Index: 5309736 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #19