Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2926 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3886. Min Range: -5.3886
Max Act: 5.3886. Min Act: -0.1700
Data Index: 8000789 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3886. Min Range: -5.3886
Max Act: 5.3574. Min Act: -0.1700
Data Index: 819053 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3886. Min Range: -5.3886
Max Act: 5.2949. Min Act: -0.1700
Data Index: 5023588 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3886. Min Range: -5.3886
Max Act: 5.2949. Min Act: -0.1700
Data Index: 1993920 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3886. Min Range: -5.3886
Max Act: 5.2324. Min Act: -0.1700
Data Index: 1861305 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3886. Min Range: -5.3886
Max Act: 5.2324. Min Act: -0.1700
Data Index: 541580 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3886. Min Range: -5.3886
Max Act: 5.2011. Min Act: -0.1700
Data Index: 1339188 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3886. Min Range: -5.3886
Max Act: 5.2011. Min Act: -0.1700
Data Index: 1651415 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3886. Min Range: -5.3886
Max Act: 5.1386. Min Act: -0.1700
Data Index: 4272580 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3886. Min Range: -5.3886
Max Act: 5.1699. Min Act: -0.1700
Data Index: 7916285 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3886. Min Range: -5.3886
Max Act: 5.1699. Min Act: -0.1700
Data Index: 1539556 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3886. Min Range: -5.3886
Max Act: 5.1699. Min Act: -0.1700
Data Index: 8424978 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3886. Min Range: -5.3886
Max Act: 5.1386. Min Act: -0.1700
Data Index: 1383789 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3886. Min Range: -5.3886
Max Act: 5.1386. Min Act: -0.1700
Data Index: 7049355 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3886. Min Range: -5.3886
Max Act: 5.1386. Min Act: -0.1700
Data Index: 5775611 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3886. Min Range: -5.3886
Max Act: 5.1386. Min Act: -0.1700
Data Index: 392370 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3886. Min Range: -5.3886
Max Act: 5.1074. Min Act: -0.1700
Data Index: 1573367 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3886. Min Range: -5.3886
Max Act: 5.0761. Min Act: -0.1700
Data Index: 7257520 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3886. Min Range: -5.3886
Max Act: 5.0761. Min Act: -0.1700
Data Index: 3929220 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3886. Min Range: -5.3886
Max Act: 5.0761. Min Act: -0.1700
Data Index: 6578721 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #19