Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2988 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3177. Min Range: -6.3177
Max Act: 6.3177. Min Act: -0.1700
Data Index: 6931612 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3177. Min Range: -6.3177
Max Act: 6.3177. Min Act: -0.1700
Data Index: 4700091 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3177. Min Range: -6.3177
Max Act: 6.1927. Min Act: -0.1700
Data Index: 8639986 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3177. Min Range: -6.3177
Max Act: 6.1302. Min Act: -0.1700
Data Index: 5541670 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3177. Min Range: -6.3177
Max Act: 6.0364. Min Act: -0.1700
Data Index: 7827449 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3177. Min Range: -6.3177
Max Act: 6.0364. Min Act: -0.1700
Data Index: 6296663 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3177. Min Range: -6.3177
Max Act: 6.0364. Min Act: -0.1700
Data Index: 6387674 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3177. Min Range: -6.3177
Max Act: 6.0052. Min Act: -0.1700
Data Index: 5878555 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3177. Min Range: -6.3177
Max Act: 6.0364. Min Act: -0.1700
Data Index: 1346243 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3177. Min Range: -6.3177
Max Act: 6.0052. Min Act: -0.1700
Data Index: 6245017 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3177. Min Range: -6.3177
Max Act: 6.0052. Min Act: -0.1700
Data Index: 2562166 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3177. Min Range: -6.3177
Max Act: 5.9427. Min Act: -0.1700
Data Index: 7211510 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3177. Min Range: -6.3177
Max Act: 5.9739. Min Act: -0.1700
Data Index: 493394 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3177. Min Range: -6.3177
Max Act: 5.9427. Min Act: -0.1700
Data Index: 6480027 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3177. Min Range: -6.3177
Max Act: 5.9427. Min Act: -0.1700
Data Index: 224504 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3177. Min Range: -6.3177
Max Act: 5.9427. Min Act: -0.1700
Data Index: 1142772 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3177. Min Range: -6.3177
Max Act: 5.9427. Min Act: -0.1700
Data Index: 4074359 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3177. Min Range: -6.3177
Max Act: 5.9114. Min Act: -0.1700
Data Index: 5638369 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3177. Min Range: -6.3177
Max Act: 5.9114. Min Act: -0.1700
Data Index: 6446497 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3177. Min Range: -6.3177
Max Act: 5.9427. Min Act: -0.1700
Data Index: 4914540 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #19