Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4130 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3787. Min Range: -7.3787
Max Act: 7.3787. Min Act: -0.1700
Data Index: 99326 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3787. Min Range: -7.3787
Max Act: 7.3787. Min Act: -0.1700
Data Index: 7600399 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3787. Min Range: -7.3787
Max Act: 7.0037. Min Act: -0.1700
Data Index: 6289558 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3787. Min Range: -7.3787
Max Act: 6.9412. Min Act: -0.1700
Data Index: 4977857 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3787. Min Range: -7.3787
Max Act: 6.9100. Min Act: -0.1700
Data Index: 71974 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3787. Min Range: -7.3787
Max Act: 6.8787. Min Act: -0.1700
Data Index: 5202106 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3787. Min Range: -7.3787
Max Act: 6.8162. Min Act: -0.1700
Data Index: 1093118 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3787. Min Range: -7.3787
Max Act: 6.8475. Min Act: -0.1700
Data Index: 5099477 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3787. Min Range: -7.3787
Max Act: 6.8475. Min Act: -0.1700
Data Index: 3639576 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3787. Min Range: -7.3787
Max Act: 6.7537. Min Act: -0.1700
Data Index: 2987841 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3787. Min Range: -7.3787
Max Act: 6.7537. Min Act: -0.1700
Data Index: 5170017 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3787. Min Range: -7.3787
Max Act: 6.7225. Min Act: -0.1700
Data Index: 7419233 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3787. Min Range: -7.3787
Max Act: 6.7225. Min Act: -0.1700
Data Index: 4586022 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3787. Min Range: -7.3787
Max Act: 6.7537. Min Act: -0.1700
Data Index: 2635530 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3787. Min Range: -7.3787
Max Act: 6.6912. Min Act: -0.1700
Data Index: 8789667 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3787. Min Range: -7.3787
Max Act: 6.7225. Min Act: -0.1700
Data Index: 2514492 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3787. Min Range: -7.3787
Max Act: 6.6912. Min Act: -0.1700
Data Index: 3336251 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3787. Min Range: -7.3787
Max Act: 6.6600. Min Act: -0.1700
Data Index: 3702120 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3787. Min Range: -7.3787
Max Act: 6.6600. Min Act: -0.1700
Data Index: 3669690 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3787. Min Range: -7.3787
Max Act: 6.6600. Min Act: -0.1700
Data Index: 3902128 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #19