Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5053 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7733. Min Range: -6.7733
Max Act: 6.7733. Min Act: -0.1700
Data Index: 7057803 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7733. Min Range: -6.7733
Max Act: 6.6795. Min Act: -0.1700
Data Index: 3588508 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7733. Min Range: -6.7733
Max Act: 6.6483. Min Act: -0.1700
Data Index: 223962 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7733. Min Range: -6.7733
Max Act: 6.6483. Min Act: -0.1700
Data Index: 7701522 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7733. Min Range: -6.7733
Max Act: 6.6170. Min Act: -0.1700
Data Index: 1725602 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7733. Min Range: -6.7733
Max Act: 6.6170. Min Act: -0.1700
Data Index: 6573017 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7733. Min Range: -6.7733
Max Act: 6.5545. Min Act: -0.1700
Data Index: 5397347 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7733. Min Range: -6.7733
Max Act: 6.5233. Min Act: -0.1700
Data Index: 5167090 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7733. Min Range: -6.7733
Max Act: 6.3983. Min Act: -0.1700
Data Index: 3704530 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7733. Min Range: -6.7733
Max Act: 6.4295. Min Act: -0.1700
Data Index: 3725587 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7733. Min Range: -6.7733
Max Act: 6.3983. Min Act: -0.1700
Data Index: 8194752 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7733. Min Range: -6.7733
Max Act: 6.3670. Min Act: -0.1700
Data Index: 4513679 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7733. Min Range: -6.7733
Max Act: 6.3670. Min Act: -0.1700
Data Index: 2133282 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7733. Min Range: -6.7733
Max Act: 6.3670. Min Act: -0.1700
Data Index: 6471335 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7733. Min Range: -6.7733
Max Act: 6.3670. Min Act: -0.1700
Data Index: 1840871 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7733. Min Range: -6.7733
Max Act: 6.3670. Min Act: -0.1700
Data Index: 7482621 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7733. Min Range: -6.7733
Max Act: 6.3670. Min Act: -0.1700
Data Index: 8118782 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7733. Min Range: -6.7733
Max Act: 6.3670. Min Act: -0.1700
Data Index: 142361 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7733. Min Range: -6.7733
Max Act: 6.3670. Min Act: -0.1700
Data Index: 2514644 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7733. Min Range: -6.7733
Max Act: 6.3358. Min Act: -0.1700
Data Index: 1080959 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #19