Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2996 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0262. Min Range: -6.0262
Max Act: 6.0262. Min Act: -0.1700
Data Index: 1682247 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0262. Min Range: -6.0262
Max Act: 5.9324. Min Act: -0.1700
Data Index: 6099279 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0262. Min Range: -6.0262
Max Act: 5.8699. Min Act: -0.1700
Data Index: 1708572 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0262. Min Range: -6.0262
Max Act: 5.8699. Min Act: -0.1700
Data Index: 3980461 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0262. Min Range: -6.0262
Max Act: 5.8699. Min Act: -0.1700
Data Index: 4935895 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0262. Min Range: -6.0262
Max Act: 5.8699. Min Act: -0.1700
Data Index: 2637029 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0262. Min Range: -6.0262
Max Act: 5.8387. Min Act: -0.1700
Data Index: 3983840 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0262. Min Range: -6.0262
Max Act: 5.8074. Min Act: -0.1700
Data Index: 2041978 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0262. Min Range: -6.0262
Max Act: 5.8074. Min Act: -0.1700
Data Index: 1667862 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0262. Min Range: -6.0262
Max Act: 5.8387. Min Act: -0.1700
Data Index: 4451207 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0262. Min Range: -6.0262
Max Act: 5.7762. Min Act: -0.1700
Data Index: 2508407 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0262. Min Range: -6.0262
Max Act: 5.7449. Min Act: -0.1700
Data Index: 1976099 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0262. Min Range: -6.0262
Max Act: 5.7762. Min Act: -0.1700
Data Index: 976307 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0262. Min Range: -6.0262
Max Act: 5.7449. Min Act: -0.1700
Data Index: 3323830 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0262. Min Range: -6.0262
Max Act: 5.7449. Min Act: -0.1700
Data Index: 8486494 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0262. Min Range: -6.0262
Max Act: 5.7449. Min Act: -0.1700
Data Index: 148269 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0262. Min Range: -6.0262
Max Act: 5.7449. Min Act: -0.1700
Data Index: 1533613 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0262. Min Range: -6.0262
Max Act: 5.7449. Min Act: -0.1700
Data Index: 2870150 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0262. Min Range: -6.0262
Max Act: 5.7449. Min Act: -0.1700
Data Index: 4331766 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0262. Min Range: -6.0262
Max Act: 5.7137. Min Act: -0.1700
Data Index: 3487091 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #19