Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3388 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4003. Min Range: -8.4003
Max Act: 8.4003. Min Act: -0.1700
Data Index: 6078224 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4003. Min Range: -8.4003
Max Act: 8.4003. Min Act: -0.1700
Data Index: 4919079 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4003. Min Range: -8.4003
Max Act: 8.2753. Min Act: -0.1700
Data Index: 2922587 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4003. Min Range: -8.4003
Max Act: 8.0878. Min Act: -0.1700
Data Index: 8703035 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4003. Min Range: -8.4003
Max Act: 8.1503. Min Act: -0.1700
Data Index: 5361818 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4003. Min Range: -8.4003
Max Act: 8.0253. Min Act: -0.1700
Data Index: 6520295 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4003. Min Range: -8.4003
Max Act: 8.0878. Min Act: -0.1700
Data Index: 3514317 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4003. Min Range: -8.4003
Max Act: 8.0878. Min Act: -0.1700
Data Index: 6155116 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4003. Min Range: -8.4003
Max Act: 8.0878. Min Act: -0.1700
Data Index: 4394632 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4003. Min Range: -8.4003
Max Act: 8.0878. Min Act: -0.1700
Data Index: 7904610 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4003. Min Range: -8.4003
Max Act: 8.0253. Min Act: -0.1700
Data Index: 1780527 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4003. Min Range: -8.4003
Max Act: 8.0253. Min Act: -0.1700
Data Index: 4641750 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4003. Min Range: -8.4003
Max Act: 8.0253. Min Act: -0.1700
Data Index: 6327776 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4003. Min Range: -8.4003
Max Act: 7.9628. Min Act: -0.1700
Data Index: 6848067 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4003. Min Range: -8.4003
Max Act: 7.9628. Min Act: -0.1700
Data Index: 4646529 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4003. Min Range: -8.4003
Max Act: 7.9628. Min Act: -0.1700
Data Index: 496585 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4003. Min Range: -8.4003
Max Act: 7.9316. Min Act: -0.1700
Data Index: 1078201 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4003. Min Range: -8.4003
Max Act: 7.9003. Min Act: -0.1700
Data Index: 7595495 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4003. Min Range: -8.4003
Max Act: 7.9003. Min Act: -0.1700
Data Index: 5330814 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4003. Min Range: -8.4003
Max Act: 7.8691. Min Act: -0.1700
Data Index: 2048129 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #19