Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2766 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2796. Min Range: -7.2796
Max Act: 7.2796. Min Act: -0.1700
Data Index: 7058639 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2796. Min Range: -7.2796
Max Act: 7.0921. Min Act: -0.1700
Data Index: 8436110 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2796. Min Range: -7.2796
Max Act: 7.0921. Min Act: -0.1700
Data Index: 4572106 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2796. Min Range: -7.2796
Max Act: 7.0296. Min Act: -0.1700
Data Index: 8551070 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2796. Min Range: -7.2796
Max Act: 6.9984. Min Act: -0.1700
Data Index: 4445958 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2796. Min Range: -7.2796
Max Act: 6.9671. Min Act: -0.1700
Data Index: 1844345 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2796. Min Range: -7.2796
Max Act: 6.9671. Min Act: -0.1700
Data Index: 8397638 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2796. Min Range: -7.2796
Max Act: 6.9671. Min Act: -0.1700
Data Index: 8795458 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2796. Min Range: -7.2796
Max Act: 6.9359. Min Act: -0.1700
Data Index: 1162351 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2796. Min Range: -7.2796
Max Act: 6.9046. Min Act: -0.1700
Data Index: 3659431 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2796. Min Range: -7.2796
Max Act: 6.9046. Min Act: -0.1700
Data Index: 1627673 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2796. Min Range: -7.2796
Max Act: 6.9046. Min Act: -0.1700
Data Index: 5904810 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2796. Min Range: -7.2796
Max Act: 6.9046. Min Act: -0.1700
Data Index: 3614318 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2796. Min Range: -7.2796
Max Act: 6.9046. Min Act: -0.1700
Data Index: 7649148 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2796. Min Range: -7.2796
Max Act: 6.8734. Min Act: -0.1700
Data Index: 5954840 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2796. Min Range: -7.2796
Max Act: 6.8734. Min Act: -0.1700
Data Index: 6184375 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2796. Min Range: -7.2796
Max Act: 6.8734. Min Act: -0.1700
Data Index: 5120257 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2796. Min Range: -7.2796
Max Act: 6.8421. Min Act: -0.1700
Data Index: 3147065 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2796. Min Range: -7.2796
Max Act: 6.8421. Min Act: -0.1700
Data Index: 6729905 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2796. Min Range: -7.2796
Max Act: 6.8421. Min Act: -0.1700
Data Index: 3269790 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #19