Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 677 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2401. Min Range: -4.2401
Max Act: 4.2401. Min Act: -0.1700
Data Index: 32686 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2401. Min Range: -4.2401
Max Act: 4.1776. Min Act: -0.1700
Data Index: 6228139 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2401. Min Range: -4.2401
Max Act: 4.1463. Min Act: -0.1700
Data Index: 3231243 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2401. Min Range: -4.2401
Max Act: 4.1776. Min Act: -0.1700
Data Index: 3310719 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2401. Min Range: -4.2401
Max Act: 4.1776. Min Act: -0.1700
Data Index: 3019683 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2401. Min Range: -4.2401
Max Act: 4.1463. Min Act: -0.1700
Data Index: 3208307 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2401. Min Range: -4.2401
Max Act: 4.1776. Min Act: -0.1700
Data Index: 5589373 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2401. Min Range: -4.2401
Max Act: 4.1150. Min Act: -0.1700
Data Index: 5004485 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2401. Min Range: -4.2401
Max Act: 4.1463. Min Act: -0.1700
Data Index: 3293676 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2401. Min Range: -4.2401
Max Act: 4.0525. Min Act: -0.1700
Data Index: 7197603 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2401. Min Range: -4.2401
Max Act: 4.0838. Min Act: -0.1700
Data Index: 7122583 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2401. Min Range: -4.2401
Max Act: 4.0838. Min Act: -0.1700
Data Index: 1110000 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2401. Min Range: -4.2401
Max Act: 4.0838. Min Act: -0.1700
Data Index: 183882 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2401. Min Range: -4.2401
Max Act: 4.0838. Min Act: -0.1700
Data Index: 5552076 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2401. Min Range: -4.2401
Max Act: 4.0525. Min Act: -0.1700
Data Index: 8179377 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2401. Min Range: -4.2401
Max Act: 4.0525. Min Act: -0.1700
Data Index: 2282560 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2401. Min Range: -4.2401
Max Act: 4.0525. Min Act: -0.1700
Data Index: 4678777 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2401. Min Range: -4.2401
Max Act: 4.0213. Min Act: -0.1700
Data Index: 1953699 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2401. Min Range: -4.2401
Max Act: 4.0213. Min Act: -0.1700
Data Index: 5864982 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2401. Min Range: -4.2401
Max Act: 4.0213. Min Act: -0.1700
Data Index: 6026397 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #19