Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3071 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2674. Min Range: -7.2674
Max Act: 7.2674. Min Act: -0.1700
Data Index: 1776119 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2674. Min Range: -7.2674
Max Act: 7.2049. Min Act: -0.1700
Data Index: 3017663 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2674. Min Range: -7.2674
Max Act: 7.0174. Min Act: -0.1700
Data Index: 6531640 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2674. Min Range: -7.2674
Max Act: 6.9549. Min Act: -0.1700
Data Index: 3989582 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2674. Min Range: -7.2674
Max Act: 6.8299. Min Act: -0.1700
Data Index: 1727856 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2674. Min Range: -7.2674
Max Act: 6.6424. Min Act: -0.1700
Data Index: 961365 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2674. Min Range: -7.2674
Max Act: 6.5486. Min Act: -0.1700
Data Index: 4709172 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2674. Min Range: -7.2674
Max Act: 6.4861. Min Act: -0.1700
Data Index: 6940863 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2674. Min Range: -7.2674
Max Act: 6.4549. Min Act: -0.1700
Data Index: 4338485 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2674. Min Range: -7.2674
Max Act: 6.4549. Min Act: -0.1700
Data Index: 464236 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2674. Min Range: -7.2674
Max Act: 6.4236. Min Act: -0.1700
Data Index: 839024 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2674. Min Range: -7.2674
Max Act: 6.3924. Min Act: -0.1700
Data Index: 4635215 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2674. Min Range: -7.2674
Max Act: 6.3611. Min Act: -0.1700
Data Index: 7048069 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2674. Min Range: -7.2674
Max Act: 6.2986. Min Act: -0.1700
Data Index: 597037 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2674. Min Range: -7.2674
Max Act: 6.3299. Min Act: -0.1700
Data Index: 1290787 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2674. Min Range: -7.2674
Max Act: 6.2674. Min Act: -0.1700
Data Index: 2037134 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2674. Min Range: -7.2674
Max Act: 6.2674. Min Act: -0.1700
Data Index: 2476051 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2674. Min Range: -7.2674
Max Act: 6.2049. Min Act: -0.1700
Data Index: 6966777 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2674. Min Range: -7.2674
Max Act: 6.2361. Min Act: -0.1700
Data Index: 7123245 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2674. Min Range: -7.2674
Max Act: 6.2674. Min Act: -0.1700
Data Index: 5473845 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #19