Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 248 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2733. Min Range: -7.2733
Max Act: 7.2733. Min Act: -0.1700
Data Index: 6942270 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2733. Min Range: -7.2733
Max Act: 7.0858. Min Act: -0.1700
Data Index: 116911 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2733. Min Range: -7.2733
Max Act: 6.9608. Min Act: -0.1700
Data Index: 8746748 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2733. Min Range: -7.2733
Max Act: 6.8983. Min Act: -0.1700
Data Index: 973258 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2733. Min Range: -7.2733
Max Act: 6.7420. Min Act: -0.1700
Data Index: 475459 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2733. Min Range: -7.2733
Max Act: 6.7733. Min Act: -0.1700
Data Index: 2228889 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2733. Min Range: -7.2733
Max Act: 6.7420. Min Act: -0.1700
Data Index: 6321034 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2733. Min Range: -7.2733
Max Act: 6.7420. Min Act: -0.1700
Data Index: 4024201 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2733. Min Range: -7.2733
Max Act: 6.7108. Min Act: -0.1700
Data Index: 6872175 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2733. Min Range: -7.2733
Max Act: 6.6483. Min Act: -0.1700
Data Index: 8620192 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2733. Min Range: -7.2733
Max Act: 6.6170. Min Act: -0.1700
Data Index: 6903316 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2733. Min Range: -7.2733
Max Act: 6.6170. Min Act: -0.1700
Data Index: 6118712 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2733. Min Range: -7.2733
Max Act: 6.6170. Min Act: -0.1700
Data Index: 5061394 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2733. Min Range: -7.2733
Max Act: 6.6483. Min Act: -0.1700
Data Index: 275490 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2733. Min Range: -7.2733
Max Act: 6.5858. Min Act: -0.1700
Data Index: 6723574 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2733. Min Range: -7.2733
Max Act: 6.6170. Min Act: -0.1700
Data Index: 721941 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2733. Min Range: -7.2733
Max Act: 6.5858. Min Act: -0.1700
Data Index: 1099325 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2733. Min Range: -7.2733
Max Act: 6.5858. Min Act: -0.1700
Data Index: 2527618 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2733. Min Range: -7.2733
Max Act: 6.5545. Min Act: -0.1700
Data Index: 3694803 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2733. Min Range: -7.2733
Max Act: 6.5545. Min Act: -0.1700
Data Index: 823256 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #19