Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4378 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6374. Min Range: -5.6374
Max Act: 5.6374. Min Act: -0.1700
Data Index: 6405744 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6374. Min Range: -5.6374
Max Act: 5.6061. Min Act: -0.1700
Data Index: 2120841 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6374. Min Range: -5.6374
Max Act: 5.6061. Min Act: -0.1700
Data Index: 6126287 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6374. Min Range: -5.6374
Max Act: 5.5749. Min Act: -0.1700
Data Index: 4050721 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6374. Min Range: -5.6374
Max Act: 5.5436. Min Act: -0.1700
Data Index: 968665 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6374. Min Range: -5.6374
Max Act: 5.5436. Min Act: -0.1700
Data Index: 73337 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6374. Min Range: -5.6374
Max Act: 5.5124. Min Act: -0.1700
Data Index: 3444898 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6374. Min Range: -5.6374
Max Act: 5.5436. Min Act: -0.1700
Data Index: 3384319 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6374. Min Range: -5.6374
Max Act: 5.4499. Min Act: -0.1700
Data Index: 6976186 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6374. Min Range: -5.6374
Max Act: 5.4499. Min Act: -0.1700
Data Index: 5307406 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6374. Min Range: -5.6374
Max Act: 5.4499. Min Act: -0.1700
Data Index: 5635409 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6374. Min Range: -5.6374
Max Act: 5.4499. Min Act: -0.1700
Data Index: 7856068 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6374. Min Range: -5.6374
Max Act: 5.4499. Min Act: -0.1700
Data Index: 8023631 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6374. Min Range: -5.6374
Max Act: 5.4186. Min Act: -0.1700
Data Index: 2645300 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6374. Min Range: -5.6374
Max Act: 5.3561. Min Act: -0.1700
Data Index: 4246562 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6374. Min Range: -5.6374
Max Act: 5.3561. Min Act: -0.1700
Data Index: 4666175 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6374. Min Range: -5.6374
Max Act: 5.3249. Min Act: -0.1700
Data Index: 1605086 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6374. Min Range: -5.6374
Max Act: 5.2311. Min Act: -0.1700
Data Index: 4711750 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6374. Min Range: -5.6374
Max Act: 5.2311. Min Act: -0.1700
Data Index: 7417143 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6374. Min Range: -5.6374
Max Act: 5.1999. Min Act: -0.1700
Data Index: 2795352 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #19