Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3059 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1411. Min Range: -6.1411
Max Act: 6.1411. Min Act: -0.1700
Data Index: 1429848 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1411. Min Range: -6.1411
Max Act: 6.0786. Min Act: -0.1700
Data Index: 2983689 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1411. Min Range: -6.1411
Max Act: 6.0161. Min Act: -0.1700
Data Index: 3126440 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1411. Min Range: -6.1411
Max Act: 5.9849. Min Act: -0.1700
Data Index: 6363455 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1411. Min Range: -6.1411
Max Act: 5.9536. Min Act: -0.1700
Data Index: 6745343 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1411. Min Range: -6.1411
Max Act: 5.9536. Min Act: -0.1700
Data Index: 2111149 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1411. Min Range: -6.1411
Max Act: 5.9536. Min Act: -0.1700
Data Index: 3367986 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1411. Min Range: -6.1411
Max Act: 5.8911. Min Act: -0.1700
Data Index: 728254 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1411. Min Range: -6.1411
Max Act: 5.9224. Min Act: -0.1700
Data Index: 8288048 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1411. Min Range: -6.1411
Max Act: 5.8911. Min Act: -0.1700
Data Index: 3059700 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1411. Min Range: -6.1411
Max Act: 5.9224. Min Act: -0.1700
Data Index: 617115 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1411. Min Range: -6.1411
Max Act: 5.9224. Min Act: -0.1700
Data Index: 8237116 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1411. Min Range: -6.1411
Max Act: 5.8599. Min Act: -0.1700
Data Index: 4716888 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1411. Min Range: -6.1411
Max Act: 5.9224. Min Act: -0.1700
Data Index: 7628335 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1411. Min Range: -6.1411
Max Act: 5.9224. Min Act: -0.1700
Data Index: 7060220 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1411. Min Range: -6.1411
Max Act: 5.8599. Min Act: -0.1700
Data Index: 7530709 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1411. Min Range: -6.1411
Max Act: 5.8599. Min Act: -0.1700
Data Index: 3720782 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1411. Min Range: -6.1411
Max Act: 5.8599. Min Act: -0.1700
Data Index: 2738322 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1411. Min Range: -6.1411
Max Act: 5.8599. Min Act: -0.1700
Data Index: 4224717 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1411. Min Range: -6.1411
Max Act: 5.7974. Min Act: -0.1700
Data Index: 6371529 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #19