Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3911 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.1099. Min Range: -6.1099
Max Act: 6.1099. Min Act: -0.1700
Data Index: 5195956 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1099. Min Range: -6.1099
Max Act: 6.0786. Min Act: -0.1700
Data Index: 4750675 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1099. Min Range: -6.1099
Max Act: 5.8911. Min Act: -0.1700
Data Index: 7837315 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1099. Min Range: -6.1099
Max Act: 5.9224. Min Act: -0.1700
Data Index: 6038431 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1099. Min Range: -6.1099
Max Act: 5.8599. Min Act: -0.1700
Data Index: 7442153 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1099. Min Range: -6.1099
Max Act: 5.8599. Min Act: -0.1700
Data Index: 2059269 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1099. Min Range: -6.1099
Max Act: 5.7661. Min Act: -0.1700
Data Index: 6181238 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1099. Min Range: -6.1099
Max Act: 5.7349. Min Act: -0.1700
Data Index: 6216501 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1099. Min Range: -6.1099
Max Act: 5.7661. Min Act: -0.1700
Data Index: 4509030 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1099. Min Range: -6.1099
Max Act: 5.7661. Min Act: -0.1700
Data Index: 3347128 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1099. Min Range: -6.1099
Max Act: 5.7349. Min Act: -0.1700
Data Index: 3700554 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1099. Min Range: -6.1099
Max Act: 5.6099. Min Act: -0.1700
Data Index: 8482908 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1099. Min Range: -6.1099
Max Act: 5.6411. Min Act: -0.1700
Data Index: 3091192 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1099. Min Range: -6.1099
Max Act: 5.6099. Min Act: -0.1700
Data Index: 5708198 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1099. Min Range: -6.1099
Max Act: 5.6099. Min Act: -0.1700
Data Index: 5343201 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1099. Min Range: -6.1099
Max Act: 5.6099. Min Act: -0.1700
Data Index: 7873020 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1099. Min Range: -6.1099
Max Act: 5.5786. Min Act: -0.1700
Data Index: 7609719 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1099. Min Range: -6.1099
Max Act: 5.5786. Min Act: -0.1700
Data Index: 1019418 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1099. Min Range: -6.1099
Max Act: 5.5161. Min Act: -0.1700
Data Index: 5708988 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1099. Min Range: -6.1099
Max Act: 5.5474. Min Act: -0.1700
Data Index: 4453452 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #19