Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1591 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3123. Min Range: -7.3123
Max Act: 7.3123. Min Act: -0.1700
Data Index: 2441966 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3123. Min Range: -7.3123
Max Act: 6.9373. Min Act: -0.1700
Data Index: 1816330 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3123. Min Range: -7.3123
Max Act: 6.8436. Min Act: -0.1700
Data Index: 7962005 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3123. Min Range: -7.3123
Max Act: 6.8123. Min Act: -0.1700
Data Index: 1864671 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3123. Min Range: -7.3123
Max Act: 6.7498. Min Act: -0.1700
Data Index: 2987835 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3123. Min Range: -7.3123
Max Act: 6.7498. Min Act: -0.1700
Data Index: 4492221 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3123. Min Range: -7.3123
Max Act: 6.7186. Min Act: -0.1700
Data Index: 8732529 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3123. Min Range: -7.3123
Max Act: 6.7186. Min Act: -0.1700
Data Index: 120404 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3123. Min Range: -7.3123
Max Act: 6.6873. Min Act: -0.1700
Data Index: 2402106 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3123. Min Range: -7.3123
Max Act: 6.6873. Min Act: -0.1700
Data Index: 5331050 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3123. Min Range: -7.3123
Max Act: 6.6873. Min Act: -0.1700
Data Index: 7753053 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3123. Min Range: -7.3123
Max Act: 6.6561. Min Act: -0.1700
Data Index: 2509756 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3123. Min Range: -7.3123
Max Act: 6.6248. Min Act: -0.1700
Data Index: 4015851 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3123. Min Range: -7.3123
Max Act: 6.5623. Min Act: -0.1700
Data Index: 2938888 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3123. Min Range: -7.3123
Max Act: 6.5623. Min Act: -0.1700
Data Index: 7915755 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3123. Min Range: -7.3123
Max Act: 6.5311. Min Act: -0.1700
Data Index: 652619 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3123. Min Range: -7.3123
Max Act: 6.5623. Min Act: -0.1700
Data Index: 316142 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3123. Min Range: -7.3123
Max Act: 6.5623. Min Act: -0.1700
Data Index: 1385300 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3123. Min Range: -7.3123
Max Act: 6.5311. Min Act: -0.1700
Data Index: 8066743 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3123. Min Range: -7.3123
Max Act: 6.5311. Min Act: -0.1700
Data Index: 3142151 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #19