Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4565 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5545. Min Range: -7.5545
Max Act: 7.5545. Min Act: -0.1700
Data Index: 3562811 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5545. Min Range: -7.5545
Max Act: 7.0545. Min Act: -0.1700
Data Index: 467141 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5545. Min Range: -7.5545
Max Act: 6.9920. Min Act: -0.1700
Data Index: 7174740 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5545. Min Range: -7.5545
Max Act: 6.8982. Min Act: -0.1700
Data Index: 3600520 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5545. Min Range: -7.5545
Max Act: 6.8670. Min Act: -0.1700
Data Index: 8659445 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5545. Min Range: -7.5545
Max Act: 6.8357. Min Act: -0.1700
Data Index: 1223026 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5545. Min Range: -7.5545
Max Act: 6.8045. Min Act: -0.1700
Data Index: 1812902 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5545. Min Range: -7.5545
Max Act: 6.7420. Min Act: -0.1700
Data Index: 7359622 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5545. Min Range: -7.5545
Max Act: 6.7420. Min Act: -0.1700
Data Index: 1465201 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5545. Min Range: -7.5545
Max Act: 6.7107. Min Act: -0.1700
Data Index: 6469463 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5545. Min Range: -7.5545
Max Act: 6.6795. Min Act: -0.1700
Data Index: 4000774 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5545. Min Range: -7.5545
Max Act: 6.6482. Min Act: -0.1700
Data Index: 5522689 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5545. Min Range: -7.5545
Max Act: 6.6170. Min Act: -0.1700
Data Index: 6688770 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5545. Min Range: -7.5545
Max Act: 6.6170. Min Act: -0.1700
Data Index: 5897740 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5545. Min Range: -7.5545
Max Act: 6.6170. Min Act: -0.1700
Data Index: 1676332 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5545. Min Range: -7.5545
Max Act: 6.5857. Min Act: -0.1700
Data Index: 4037364 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5545. Min Range: -7.5545
Max Act: 6.5857. Min Act: -0.1700
Data Index: 6249603 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5545. Min Range: -7.5545
Max Act: 6.5232. Min Act: -0.1700
Data Index: 2088311 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5545. Min Range: -7.5545
Max Act: 6.5545. Min Act: -0.1700
Data Index: 3034630 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5545. Min Range: -7.5545
Max Act: 6.5232. Min Act: -0.1700
Data Index: 7831335 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #19