Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5734 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8645. Min Range: -6.8645
Max Act: 6.8645. Min Act: -0.1700
Data Index: 8615682 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8645. Min Range: -6.8645
Max Act: 6.8332. Min Act: -0.1700
Data Index: 2611077 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8645. Min Range: -6.8645
Max Act: 6.7082. Min Act: -0.1700
Data Index: 4692346 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8645. Min Range: -6.8645
Max Act: 6.7082. Min Act: -0.1700
Data Index: 5812164 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8645. Min Range: -6.8645
Max Act: 6.6145. Min Act: -0.1700
Data Index: 4238306 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8645. Min Range: -6.8645
Max Act: 6.6457. Min Act: -0.1700
Data Index: 6619575 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8645. Min Range: -6.8645
Max Act: 6.6145. Min Act: -0.1700
Data Index: 5820904 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8645. Min Range: -6.8645
Max Act: 6.5832. Min Act: -0.1700
Data Index: 1204162 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8645. Min Range: -6.8645
Max Act: 6.5832. Min Act: -0.1700
Data Index: 6142236 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8645. Min Range: -6.8645
Max Act: 6.5832. Min Act: -0.1700
Data Index: 1900633 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8645. Min Range: -6.8645
Max Act: 6.5832. Min Act: -0.1700
Data Index: 8075073 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8645. Min Range: -6.8645
Max Act: 6.5832. Min Act: -0.1700
Data Index: 3606977 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8645. Min Range: -6.8645
Max Act: 6.5520. Min Act: -0.1700
Data Index: 7493816 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8645. Min Range: -6.8645
Max Act: 6.5207. Min Act: -0.1700
Data Index: 194378 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8645. Min Range: -6.8645
Max Act: 6.4895. Min Act: -0.1700
Data Index: 3955837 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8645. Min Range: -6.8645
Max Act: 6.4895. Min Act: -0.1700
Data Index: 6489735 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8645. Min Range: -6.8645
Max Act: 6.4582. Min Act: -0.1700
Data Index: 1620161 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8645. Min Range: -6.8645
Max Act: 6.4582. Min Act: -0.1700
Data Index: 8330587 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8645. Min Range: -6.8645
Max Act: 6.3957. Min Act: -0.1700
Data Index: 310707 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8645. Min Range: -6.8645
Max Act: 6.3645. Min Act: -0.1700
Data Index: 3505158 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #19