Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3349 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6152. Min Range: -7.6152
Max Act: 7.6152. Min Act: -0.1700
Data Index: 1396404 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6152. Min Range: -7.6152
Max Act: 7.4277. Min Act: -0.1700
Data Index: 4912955 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6152. Min Range: -7.6152
Max Act: 7.3964. Min Act: -0.1700
Data Index: 114544 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6152. Min Range: -7.6152
Max Act: 7.2714. Min Act: -0.1700
Data Index: 4627327 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6152. Min Range: -7.6152
Max Act: 7.2714. Min Act: -0.1700
Data Index: 4897967 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6152. Min Range: -7.6152
Max Act: 7.1464. Min Act: -0.1700
Data Index: 5506753 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6152. Min Range: -7.6152
Max Act: 7.1152. Min Act: -0.1700
Data Index: 7397888 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6152. Min Range: -7.6152
Max Act: 7.0214. Min Act: -0.1700
Data Index: 4587584 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6152. Min Range: -7.6152
Max Act: 6.9902. Min Act: -0.1700
Data Index: 5209903 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6152. Min Range: -7.6152
Max Act: 6.9902. Min Act: -0.1700
Data Index: 1453606 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6152. Min Range: -7.6152
Max Act: 6.9277. Min Act: -0.1700
Data Index: 915405 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6152. Min Range: -7.6152
Max Act: 6.8964. Min Act: -0.1700
Data Index: 7733184 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6152. Min Range: -7.6152
Max Act: 6.8964. Min Act: -0.1700
Data Index: 2563938 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6152. Min Range: -7.6152
Max Act: 6.8339. Min Act: -0.1700
Data Index: 8806399 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6152. Min Range: -7.6152
Max Act: 6.8339. Min Act: -0.1700
Data Index: 7592166 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6152. Min Range: -7.6152
Max Act: 6.8027. Min Act: -0.1700
Data Index: 8136550 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6152. Min Range: -7.6152
Max Act: 6.7714. Min Act: -0.1700
Data Index: 6950176 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6152. Min Range: -7.6152
Max Act: 6.8027. Min Act: -0.1700
Data Index: 4482720 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6152. Min Range: -7.6152
Max Act: 6.8027. Min Act: -0.1700
Data Index: 3199557 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6152. Min Range: -7.6152
Max Act: 6.8027. Min Act: -0.1700
Data Index: 1913112 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #19