Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3315 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0082. Min Range: -4.0082
Max Act: 4.0082. Min Act: -0.1700
Data Index: 5253981 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0082. Min Range: -4.0082
Max Act: 3.8363. Min Act: -0.1700
Data Index: 2620520 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0082. Min Range: -4.0082
Max Act: 3.8206. Min Act: -0.1700
Data Index: 1637128 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0082. Min Range: -4.0082
Max Act: 3.7425. Min Act: -0.1700
Data Index: 8263636 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0082. Min Range: -4.0082
Max Act: 3.7425. Min Act: -0.1700
Data Index: 276748 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0082. Min Range: -4.0082
Max Act: 3.7268. Min Act: -0.1700
Data Index: 4606294 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0082. Min Range: -4.0082
Max Act: 3.7268. Min Act: -0.1700
Data Index: 1947342 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0082. Min Range: -4.0082
Max Act: 3.6955. Min Act: -0.1700
Data Index: 4455755 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0082. Min Range: -4.0082
Max Act: 3.6642. Min Act: -0.1700
Data Index: 2411153 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0082. Min Range: -4.0082
Max Act: 3.6642. Min Act: -0.1700
Data Index: 7745615 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0082. Min Range: -4.0082
Max Act: 3.6799. Min Act: -0.1700
Data Index: 6914292 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0082. Min Range: -4.0082
Max Act: 3.6642. Min Act: -0.1700
Data Index: 3461316 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0082. Min Range: -4.0082
Max Act: 3.6329. Min Act: -0.1700
Data Index: 8147587 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0082. Min Range: -4.0082
Max Act: 3.6016. Min Act: -0.1700
Data Index: 6847837 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0082. Min Range: -4.0082
Max Act: 3.5860. Min Act: -0.1700
Data Index: 4929123 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0082. Min Range: -4.0082
Max Act: 3.6173. Min Act: -0.1700
Data Index: 4583897 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0082. Min Range: -4.0082
Max Act: 3.6016. Min Act: -0.1700
Data Index: 7815863 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0082. Min Range: -4.0082
Max Act: 3.5860. Min Act: -0.1700
Data Index: 2774724 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0082. Min Range: -4.0082
Max Act: 3.5703. Min Act: -0.1700
Data Index: 829518 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0082. Min Range: -4.0082
Max Act: 3.5703. Min Act: -0.1700
Data Index: 3399125 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #19