Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3793 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9948. Min Range: -5.9948
Max Act: 5.9948. Min Act: -0.1700
Data Index: 848591 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9948. Min Range: -5.9948
Max Act: 5.8386. Min Act: -0.1700
Data Index: 2817149 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9948. Min Range: -5.9948
Max Act: 5.6823. Min Act: -0.1700
Data Index: 2893006 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9948. Min Range: -5.9948
Max Act: 5.5261. Min Act: -0.1700
Data Index: 7688772 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9948. Min Range: -5.9948
Max Act: 5.5261. Min Act: -0.1700
Data Index: 3324259 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9948. Min Range: -5.9948
Max Act: 5.5261. Min Act: -0.1700
Data Index: 5967044 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9948. Min Range: -5.9948
Max Act: 5.5573. Min Act: -0.1700
Data Index: 1028158 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9948. Min Range: -5.9948
Max Act: 5.4948. Min Act: -0.1700
Data Index: 3503204 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9948. Min Range: -5.9948
Max Act: 5.4636. Min Act: -0.1700
Data Index: 7688785 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9948. Min Range: -5.9948
Max Act: 5.4636. Min Act: -0.1700
Data Index: 7760116 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9948. Min Range: -5.9948
Max Act: 5.4323. Min Act: -0.1700
Data Index: 2242156 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9948. Min Range: -5.9948
Max Act: 5.4323. Min Act: -0.1700
Data Index: 1459339 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9948. Min Range: -5.9948
Max Act: 5.4011. Min Act: -0.1700
Data Index: 8249192 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9948. Min Range: -5.9948
Max Act: 5.4011. Min Act: -0.1700
Data Index: 8306498 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9948. Min Range: -5.9948
Max Act: 5.4011. Min Act: -0.1700
Data Index: 1047526 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9948. Min Range: -5.9948
Max Act: 5.4011. Min Act: -0.1700
Data Index: 2098789 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9948. Min Range: -5.9948
Max Act: 5.3698. Min Act: -0.1700
Data Index: 1556244 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9948. Min Range: -5.9948
Max Act: 5.3386. Min Act: -0.1700
Data Index: 6677722 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9948. Min Range: -5.9948
Max Act: 5.3386. Min Act: -0.1700
Data Index: 6323508 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9948. Min Range: -5.9948
Max Act: 5.3386. Min Act: -0.1700
Data Index: 5093675 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #19