Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4033 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2853. Min Range: -4.2853
Max Act: 4.2853. Min Act: -0.1700
Data Index: 1265452 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2853. Min Range: -4.2853
Max Act: 4.2228. Min Act: -0.1700
Data Index: 5252389 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2853. Min Range: -4.2853
Max Act: 4.2228. Min Act: -0.1700
Data Index: 1202257 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2853. Min Range: -4.2853
Max Act: 4.1916. Min Act: -0.1700
Data Index: 4285612 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2853. Min Range: -4.2853
Max Act: 4.1291. Min Act: -0.1700
Data Index: 5514108 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2853. Min Range: -4.2853
Max Act: 4.0978. Min Act: -0.1700
Data Index: 1928721 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2853. Min Range: -4.2853
Max Act: 4.1291. Min Act: -0.1700
Data Index: 6793589 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2853. Min Range: -4.2853
Max Act: 4.0978. Min Act: -0.1700
Data Index: 448624 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2853. Min Range: -4.2853
Max Act: 4.0665. Min Act: -0.1700
Data Index: 7522415 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2853. Min Range: -4.2853
Max Act: 4.0978. Min Act: -0.1700
Data Index: 2438234 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2853. Min Range: -4.2853
Max Act: 4.0353. Min Act: -0.1700
Data Index: 5886348 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2853. Min Range: -4.2853
Max Act: 4.0353. Min Act: -0.1700
Data Index: 4380790 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2853. Min Range: -4.2853
Max Act: 4.0353. Min Act: -0.1700
Data Index: 5994261 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2853. Min Range: -4.2853
Max Act: 4.0040. Min Act: -0.1700
Data Index: 1616338 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2853. Min Range: -4.2853
Max Act: 4.0040. Min Act: -0.1700
Data Index: 7136077 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2853. Min Range: -4.2853
Max Act: 4.0040. Min Act: -0.1700
Data Index: 3845075 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2853. Min Range: -4.2853
Max Act: 4.0040. Min Act: -0.1700
Data Index: 3722116 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2853. Min Range: -4.2853
Max Act: 4.0040. Min Act: -0.1700
Data Index: 7596333 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2853. Min Range: -4.2853
Max Act: 4.0040. Min Act: -0.1700
Data Index: 5607595 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2853. Min Range: -4.2853
Max Act: 4.0040. Min Act: -0.1700
Data Index: 6376242 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #19