Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3423 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5916. Min Range: -5.5916
Max Act: 5.5916. Min Act: -0.1700
Data Index: 6169129 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5916. Min Range: -5.5916
Max Act: 5.4979. Min Act: -0.1700
Data Index: 8205529 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5916. Min Range: -5.5916
Max Act: 5.4666. Min Act: -0.1700
Data Index: 8373696 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5916. Min Range: -5.5916
Max Act: 5.4354. Min Act: -0.1700
Data Index: 243195 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5916. Min Range: -5.5916
Max Act: 5.4354. Min Act: -0.1700
Data Index: 6864823 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5916. Min Range: -5.5916
Max Act: 5.3729. Min Act: -0.1700
Data Index: 5186712 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5916. Min Range: -5.5916
Max Act: 5.3729. Min Act: -0.1700
Data Index: 4317037 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5916. Min Range: -5.5916
Max Act: 5.3416. Min Act: -0.1700
Data Index: 2964741 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5916. Min Range: -5.5916
Max Act: 5.3104. Min Act: -0.1700
Data Index: 1140320 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5916. Min Range: -5.5916
Max Act: 5.3104. Min Act: -0.1700
Data Index: 1686825 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5916. Min Range: -5.5916
Max Act: 5.2479. Min Act: -0.1700
Data Index: 4612100 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5916. Min Range: -5.5916
Max Act: 5.2479. Min Act: -0.1700
Data Index: 7885787 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5916. Min Range: -5.5916
Max Act: 5.2479. Min Act: -0.1700
Data Index: 6553987 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5916. Min Range: -5.5916
Max Act: 5.2479. Min Act: -0.1700
Data Index: 3915540 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5916. Min Range: -5.5916
Max Act: 5.2479. Min Act: -0.1700
Data Index: 5659950 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5916. Min Range: -5.5916
Max Act: 5.2166. Min Act: -0.1700
Data Index: 7267322 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5916. Min Range: -5.5916
Max Act: 5.2166. Min Act: -0.1700
Data Index: 3521806 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5916. Min Range: -5.5916
Max Act: 5.2166. Min Act: -0.1700
Data Index: 2581129 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5916. Min Range: -5.5916
Max Act: 5.2166. Min Act: -0.1700
Data Index: 1871336 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5916. Min Range: -5.5916
Max Act: 5.2166. Min Act: -0.1700
Data Index: 1990310 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #19