Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2621 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2197. Min Range: -6.2197
Max Act: 6.2197. Min Act: -0.1700
Data Index: 7400216 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2197. Min Range: -6.2197
Max Act: 6.0635. Min Act: -0.1700
Data Index: 8781490 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2197. Min Range: -6.2197
Max Act: 6.0322. Min Act: -0.1700
Data Index: 572060 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2197. Min Range: -6.2197
Max Act: 5.9385. Min Act: -0.1700
Data Index: 7256349 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2197. Min Range: -6.2197
Max Act: 5.9385. Min Act: -0.1700
Data Index: 2538876 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2197. Min Range: -6.2197
Max Act: 5.9385. Min Act: -0.1700
Data Index: 691290 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2197. Min Range: -6.2197
Max Act: 5.8760. Min Act: -0.1700
Data Index: 8818521 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2197. Min Range: -6.2197
Max Act: 5.8135. Min Act: -0.1700
Data Index: 1194225 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2197. Min Range: -6.2197
Max Act: 5.7822. Min Act: -0.1700
Data Index: 516144 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2197. Min Range: -6.2197
Max Act: 5.7822. Min Act: -0.1700
Data Index: 1451627 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2197. Min Range: -6.2197
Max Act: 5.7822. Min Act: -0.1700
Data Index: 116820 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2197. Min Range: -6.2197
Max Act: 5.7822. Min Act: -0.1700
Data Index: 531029 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2197. Min Range: -6.2197
Max Act: 5.7510. Min Act: -0.1700
Data Index: 7722432 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2197. Min Range: -6.2197
Max Act: 5.7197. Min Act: -0.1700
Data Index: 7310062 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2197. Min Range: -6.2197
Max Act: 5.6885. Min Act: -0.1700
Data Index: 7294787 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2197. Min Range: -6.2197
Max Act: 5.6885. Min Act: -0.1700
Data Index: 7892816 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2197. Min Range: -6.2197
Max Act: 5.6572. Min Act: -0.1700
Data Index: 1633604 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2197. Min Range: -6.2197
Max Act: 5.6572. Min Act: -0.1700
Data Index: 3241694 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2197. Min Range: -6.2197
Max Act: 5.6572. Min Act: -0.1700
Data Index: 7105460 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2197. Min Range: -6.2197
Max Act: 5.6572. Min Act: -0.1700
Data Index: 2012412 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #19