Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1776 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6055. Min Range: -5.6055
Max Act: 5.6055. Min Act: -0.1700
Data Index: 3294409 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6055. Min Range: -5.6055
Max Act: 5.4493. Min Act: -0.1700
Data Index: 3250680 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6055. Min Range: -5.6055
Max Act: 5.3243. Min Act: -0.1700
Data Index: 8087980 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6055. Min Range: -5.6055
Max Act: 5.3243. Min Act: -0.1700
Data Index: 3289065 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6055. Min Range: -5.6055
Max Act: 5.2930. Min Act: -0.1700
Data Index: 4361744 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6055. Min Range: -5.6055
Max Act: 5.2930. Min Act: -0.1700
Data Index: 915307 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6055. Min Range: -5.6055
Max Act: 5.2930. Min Act: -0.1700
Data Index: 58456 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6055. Min Range: -5.6055
Max Act: 5.2618. Min Act: -0.1700
Data Index: 5595832 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6055. Min Range: -5.6055
Max Act: 5.2618. Min Act: -0.1700
Data Index: 2053745 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6055. Min Range: -5.6055
Max Act: 5.2618. Min Act: -0.1700
Data Index: 6236034 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6055. Min Range: -5.6055
Max Act: 5.2305. Min Act: -0.1700
Data Index: 6477534 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6055. Min Range: -5.6055
Max Act: 5.2618. Min Act: -0.1700
Data Index: 581825 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6055. Min Range: -5.6055
Max Act: 5.2305. Min Act: -0.1700
Data Index: 7194645 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6055. Min Range: -5.6055
Max Act: 5.1993. Min Act: -0.1700
Data Index: 5781327 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6055. Min Range: -5.6055
Max Act: 5.1993. Min Act: -0.1700
Data Index: 7299025 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6055. Min Range: -5.6055
Max Act: 5.1680. Min Act: -0.1700
Data Index: 286902 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6055. Min Range: -5.6055
Max Act: 5.1993. Min Act: -0.1700
Data Index: 1865923 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6055. Min Range: -5.6055
Max Act: 5.1993. Min Act: -0.1700
Data Index: 2571087 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6055. Min Range: -5.6055
Max Act: 5.1993. Min Act: -0.1700
Data Index: 6256882 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6055. Min Range: -5.6055
Max Act: 5.1993. Min Act: -0.1700
Data Index: 4046408 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #19