Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1385 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4636. Min Range: -5.4636
Max Act: 5.4636. Min Act: -0.1700
Data Index: 7131402 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4636. Min Range: -5.4636
Max Act: 5.3386. Min Act: -0.1700
Data Index: 5109478 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4636. Min Range: -5.4636
Max Act: 5.2761. Min Act: -0.1700
Data Index: 8712387 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4636. Min Range: -5.4636
Max Act: 5.1511. Min Act: -0.1700
Data Index: 2869600 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4636. Min Range: -5.4636
Max Act: 5.1511. Min Act: -0.1700
Data Index: 5366384 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4636. Min Range: -5.4636
Max Act: 5.0886. Min Act: -0.1700
Data Index: 3281448 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4636. Min Range: -5.4636
Max Act: 5.0573. Min Act: -0.1700
Data Index: 3581946 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4636. Min Range: -5.4636
Max Act: 5.0261. Min Act: -0.1700
Data Index: 3747276 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4636. Min Range: -5.4636
Max Act: 4.9948. Min Act: -0.1700
Data Index: 5660327 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4636. Min Range: -5.4636
Max Act: 4.9948. Min Act: -0.1700
Data Index: 1380069 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4636. Min Range: -5.4636
Max Act: 4.9636. Min Act: -0.1700
Data Index: 8690998 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4636. Min Range: -5.4636
Max Act: 4.9323. Min Act: -0.1700
Data Index: 5777806 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4636. Min Range: -5.4636
Max Act: 4.9323. Min Act: -0.1700
Data Index: 8690996 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4636. Min Range: -5.4636
Max Act: 4.9323. Min Act: -0.1700
Data Index: 8690997 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4636. Min Range: -5.4636
Max Act: 4.9636. Min Act: -0.1700
Data Index: 4008168 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4636. Min Range: -5.4636
Max Act: 4.9011. Min Act: -0.1700
Data Index: 3281446 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4636. Min Range: -5.4636
Max Act: 4.9011. Min Act: -0.1700
Data Index: 8691002 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4636. Min Range: -5.4636
Max Act: 4.9011. Min Act: -0.1700
Data Index: 6287182 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4636. Min Range: -5.4636
Max Act: 4.8698. Min Act: -0.1700
Data Index: 8053516 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4636. Min Range: -5.4636
Max Act: 4.8698. Min Act: -0.1700
Data Index: 5562941 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #19