Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4521 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3519. Min Range: -5.3519
Max Act: 5.3519. Min Act: -0.1700
Data Index: 1727721 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3519. Min Range: -5.3519
Max Act: 5.3519. Min Act: -0.1700
Data Index: 3693072 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3519. Min Range: -5.3519
Max Act: 5.3206. Min Act: -0.1700
Data Index: 3072587 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3519. Min Range: -5.3519
Max Act: 5.3519. Min Act: -0.1700
Data Index: 6342642 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3519. Min Range: -5.3519
Max Act: 5.3206. Min Act: -0.1700
Data Index: 3474103 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3519. Min Range: -5.3519
Max Act: 5.3206. Min Act: -0.1700
Data Index: 5023467 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3519. Min Range: -5.3519
Max Act: 5.3519. Min Act: -0.1700
Data Index: 836587 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3519. Min Range: -5.3519
Max Act: 5.2894. Min Act: -0.1700
Data Index: 4456280 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3519. Min Range: -5.3519
Max Act: 5.2581. Min Act: -0.1700
Data Index: 2598053 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3519. Min Range: -5.3519
Max Act: 5.2581. Min Act: -0.1700
Data Index: 4107954 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3519. Min Range: -5.3519
Max Act: 5.2581. Min Act: -0.1700
Data Index: 2944930 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3519. Min Range: -5.3519
Max Act: 5.2581. Min Act: -0.1700
Data Index: 7201992 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3519. Min Range: -5.3519
Max Act: 5.2269. Min Act: -0.1700
Data Index: 1912455 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3519. Min Range: -5.3519
Max Act: 5.2269. Min Act: -0.1700
Data Index: 7542113 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3519. Min Range: -5.3519
Max Act: 5.1956. Min Act: -0.1700
Data Index: 4975550 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3519. Min Range: -5.3519
Max Act: 5.1956. Min Act: -0.1700
Data Index: 164949 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3519. Min Range: -5.3519
Max Act: 5.1956. Min Act: -0.1700
Data Index: 3806784 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3519. Min Range: -5.3519
Max Act: 5.1956. Min Act: -0.1700
Data Index: 5910762 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3519. Min Range: -5.3519
Max Act: 5.1956. Min Act: -0.1700
Data Index: 4905578 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3519. Min Range: -5.3519
Max Act: 5.1956. Min Act: -0.1700
Data Index: 6627372 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #19