Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2964 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2257. Min Range: -6.2257
Max Act: 6.2257. Min Act: -0.1700
Data Index: 1315003 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2257. Min Range: -6.2257
Max Act: 6.1945. Min Act: -0.1700
Data Index: 2917324 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2257. Min Range: -6.2257
Max Act: 6.0070. Min Act: -0.1700
Data Index: 6493184 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2257. Min Range: -6.2257
Max Act: 6.0070. Min Act: -0.1700
Data Index: 4442319 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2257. Min Range: -6.2257
Max Act: 5.9445. Min Act: -0.1700
Data Index: 3607602 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2257. Min Range: -6.2257
Max Act: 5.9757. Min Act: -0.1700
Data Index: 5885109 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2257. Min Range: -6.2257
Max Act: 5.9445. Min Act: -0.1700
Data Index: 7833617 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2257. Min Range: -6.2257
Max Act: 5.9445. Min Act: -0.1700
Data Index: 8038466 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2257. Min Range: -6.2257
Max Act: 5.9445. Min Act: -0.1700
Data Index: 3777153 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2257. Min Range: -6.2257
Max Act: 5.9132. Min Act: -0.1700
Data Index: 4908058 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2257. Min Range: -6.2257
Max Act: 5.8507. Min Act: -0.1700
Data Index: 4417719 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2257. Min Range: -6.2257
Max Act: 5.8507. Min Act: -0.1700
Data Index: 4429652 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2257. Min Range: -6.2257
Max Act: 5.8507. Min Act: -0.1700
Data Index: 4744634 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2257. Min Range: -6.2257
Max Act: 5.8507. Min Act: -0.1700
Data Index: 7937617 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2257. Min Range: -6.2257
Max Act: 5.8507. Min Act: -0.1700
Data Index: 8211974 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2257. Min Range: -6.2257
Max Act: 5.8507. Min Act: -0.1700
Data Index: 1415765 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2257. Min Range: -6.2257
Max Act: 5.8507. Min Act: -0.1700
Data Index: 6209480 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2257. Min Range: -6.2257
Max Act: 5.8195. Min Act: -0.1700
Data Index: 8244826 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2257. Min Range: -6.2257
Max Act: 5.8195. Min Act: -0.1700
Data Index: 1265615 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2257. Min Range: -6.2257
Max Act: 5.8195. Min Act: -0.1700
Data Index: 4971527 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #19