Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3050 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0041. Min Range: -10.0041
Max Act: 10.0041. Min Act: -0.1700
Data Index: 5325818 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0041. Min Range: -10.0041
Max Act: 9.9416. Min Act: -0.1700
Data Index: 2533875 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0041. Min Range: -10.0041
Max Act: 9.7541. Min Act: -0.1700
Data Index: 7519743 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0041. Min Range: -10.0041
Max Act: 9.6291. Min Act: -0.1700
Data Index: 2148333 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0041. Min Range: -10.0041
Max Act: 9.5666. Min Act: -0.1700
Data Index: 3927695 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0041. Min Range: -10.0041
Max Act: 9.5666. Min Act: -0.1700
Data Index: 1379393 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0041. Min Range: -10.0041
Max Act: 9.5041. Min Act: -0.1700
Data Index: 5088261 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0041. Min Range: -10.0041
Max Act: 9.5041. Min Act: -0.1700
Data Index: 1126477 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0041. Min Range: -10.0041
Max Act: 9.4416. Min Act: -0.1696
Data Index: 1270531 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0041. Min Range: -10.0041
Max Act: 9.4416. Min Act: -0.1700
Data Index: 6060675 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0041. Min Range: -10.0041
Max Act: 9.3791. Min Act: -0.1700
Data Index: 8264570 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0041. Min Range: -10.0041
Max Act: 9.3791. Min Act: -0.1700
Data Index: 7105954 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0041. Min Range: -10.0041
Max Act: 9.3791. Min Act: -0.1700
Data Index: 897950 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0041. Min Range: -10.0041
Max Act: 9.3791. Min Act: -0.1700
Data Index: 1149217 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0041. Min Range: -10.0041
Max Act: 9.4416. Min Act: -0.1700
Data Index: 5258035 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0041. Min Range: -10.0041
Max Act: 9.3166. Min Act: -0.1700
Data Index: 984000 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0041. Min Range: -10.0041
Max Act: 9.2541. Min Act: -0.1700
Data Index: 7612859 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0041. Min Range: -10.0041
Max Act: 9.3166. Min Act: -0.1700
Data Index: 7647260 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0041. Min Range: -10.0041
Max Act: 9.2541. Min Act: -0.1700
Data Index: 6141888 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0041. Min Range: -10.0041
Max Act: 9.2541. Min Act: -0.1700
Data Index: 902070 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #19