Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1360 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4181. Min Range: -6.4181
Max Act: 6.4181. Min Act: -0.1700
Data Index: 7229062 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4181. Min Range: -6.4181
Max Act: 6.4181. Min Act: -0.1700
Data Index: 4227205 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4181. Min Range: -6.4181
Max Act: 6.3244. Min Act: -0.1700
Data Index: 8280447 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4181. Min Range: -6.4181
Max Act: 6.3244. Min Act: -0.1700
Data Index: 7191027 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4181. Min Range: -6.4181
Max Act: 6.2931. Min Act: -0.1700
Data Index: 3352924 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4181. Min Range: -6.4181
Max Act: 6.2931. Min Act: -0.1700
Data Index: 5564722 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4181. Min Range: -6.4181
Max Act: 6.2619. Min Act: -0.1700
Data Index: 5255488 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4181. Min Range: -6.4181
Max Act: 6.2306. Min Act: -0.1700
Data Index: 4342328 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4181. Min Range: -6.4181
Max Act: 6.1994. Min Act: -0.1700
Data Index: 8298465 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4181. Min Range: -6.4181
Max Act: 6.1994. Min Act: -0.1700
Data Index: 3712484 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4181. Min Range: -6.4181
Max Act: 6.1994. Min Act: -0.1700
Data Index: 7038002 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4181. Min Range: -6.4181
Max Act: 6.1994. Min Act: -0.1700
Data Index: 4432806 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4181. Min Range: -6.4181
Max Act: 6.1994. Min Act: -0.1700
Data Index: 4966193 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4181. Min Range: -6.4181
Max Act: 6.1994. Min Act: -0.1684
Data Index: 476523 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4181. Min Range: -6.4181
Max Act: 6.1681. Min Act: -0.1698
Data Index: 4339457 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4181. Min Range: -6.4181
Max Act: 6.1681. Min Act: -0.1700
Data Index: 3535272 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4181. Min Range: -6.4181
Max Act: 6.1681. Min Act: -0.1700
Data Index: 3729777 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4181. Min Range: -6.4181
Max Act: 6.1681. Min Act: -0.1700
Data Index: 4516811 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4181. Min Range: -6.4181
Max Act: 6.1369. Min Act: -0.1700
Data Index: 3133397 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4181. Min Range: -6.4181
Max Act: 6.1681. Min Act: -0.1700
Data Index: 2331538 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19