Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5063 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9038. Min Range: -5.9038
Max Act: 5.9038. Min Act: -0.1700
Data Index: 4989943 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9038. Min Range: -5.9038
Max Act: 5.8726. Min Act: -0.1700
Data Index: 237884 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9038. Min Range: -5.9038
Max Act: 5.8101. Min Act: -0.1700
Data Index: 8031409 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9038. Min Range: -5.9038
Max Act: 5.7788. Min Act: -0.1700
Data Index: 3295389 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9038. Min Range: -5.9038
Max Act: 5.7476. Min Act: -0.1700
Data Index: 7514383 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9038. Min Range: -5.9038
Max Act: 5.7476. Min Act: -0.1700
Data Index: 237883 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9038. Min Range: -5.9038
Max Act: 5.7163. Min Act: -0.1700
Data Index: 3981833 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9038. Min Range: -5.9038
Max Act: 5.6851. Min Act: -0.1700
Data Index: 5350216 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9038. Min Range: -5.9038
Max Act: 5.6226. Min Act: -0.1700
Data Index: 1222495 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9038. Min Range: -5.9038
Max Act: 5.5913. Min Act: -0.1700
Data Index: 1484618 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9038. Min Range: -5.9038
Max Act: 5.5601. Min Act: -0.1700
Data Index: 6768951 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9038. Min Range: -5.9038
Max Act: 5.5288. Min Act: -0.1700
Data Index: 7514379 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9038. Min Range: -5.9038
Max Act: 5.5288. Min Act: -0.1700
Data Index: 4656876 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9038. Min Range: -5.9038
Max Act: 5.4976. Min Act: -0.1700
Data Index: 7622453 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9038. Min Range: -5.9038
Max Act: 5.4976. Min Act: -0.1700
Data Index: 8029413 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9038. Min Range: -5.9038
Max Act: 5.4976. Min Act: -0.1700
Data Index: 700305 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9038. Min Range: -5.9038
Max Act: 5.4663. Min Act: -0.1700
Data Index: 601066 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9038. Min Range: -5.9038
Max Act: 5.4351. Min Act: -0.1700
Data Index: 1367804 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9038. Min Range: -5.9038
Max Act: 5.4663. Min Act: -0.1700
Data Index: 3158165 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9038. Min Range: -5.9038
Max Act: 5.4663. Min Act: -0.1700
Data Index: 578846 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #19