Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2642 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9044. Min Range: -7.9044
Max Act: 7.9044. Min Act: -0.1700
Data Index: 4967873 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9044. Min Range: -7.9044
Max Act: 7.7794. Min Act: -0.1700
Data Index: 5868729 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9044. Min Range: -7.9044
Max Act: 7.6857. Min Act: -0.1700
Data Index: 2168260 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9044. Min Range: -7.9044
Max Act: 7.5919. Min Act: -0.1700
Data Index: 2252958 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9044. Min Range: -7.9044
Max Act: 7.5919. Min Act: -0.1700
Data Index: 7230125 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9044. Min Range: -7.9044
Max Act: 7.5607. Min Act: -0.1700
Data Index: 8554060 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9044. Min Range: -7.9044
Max Act: 7.5294. Min Act: -0.1700
Data Index: 3760141 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9044. Min Range: -7.9044
Max Act: 7.4982. Min Act: -0.1700
Data Index: 7792296 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9044. Min Range: -7.9044
Max Act: 7.4982. Min Act: -0.1700
Data Index: 2963941 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9044. Min Range: -7.9044
Max Act: 7.4357. Min Act: -0.1700
Data Index: 4967870 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9044. Min Range: -7.9044
Max Act: 7.3419. Min Act: -0.1700
Data Index: 8212673 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9044. Min Range: -7.9044
Max Act: 7.3107. Min Act: -0.1700
Data Index: 2539215 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9044. Min Range: -7.9044
Max Act: 7.3107. Min Act: -0.1700
Data Index: 5315934 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9044. Min Range: -7.9044
Max Act: 7.3107. Min Act: -0.1700
Data Index: 2361919 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9044. Min Range: -7.9044
Max Act: 7.2794. Min Act: -0.1700
Data Index: 1055484 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9044. Min Range: -7.9044
Max Act: 7.2794. Min Act: -0.1700
Data Index: 4358620 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9044. Min Range: -7.9044
Max Act: 7.2482. Min Act: -0.1700
Data Index: 6324095 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9044. Min Range: -7.9044
Max Act: 7.2482. Min Act: -0.1700
Data Index: 4796681 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9044. Min Range: -7.9044
Max Act: 7.1857. Min Act: -0.1700
Data Index: 3147430 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9044. Min Range: -7.9044
Max Act: 7.2169. Min Act: -0.1700
Data Index: 7534773 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #19