Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3863 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0082. Min Range: -5.0082
Max Act: 5.0082. Min Act: -0.1700
Data Index: 999308 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0082. Min Range: -5.0082
Max Act: 4.9457. Min Act: -0.1700
Data Index: 999309 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0082. Min Range: -5.0082
Max Act: 4.9145. Min Act: -0.1700
Data Index: 6119263 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0082. Min Range: -5.0082
Max Act: 4.8520. Min Act: -0.1700
Data Index: 6147099 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0082. Min Range: -5.0082
Max Act: 4.8207. Min Act: -0.1700
Data Index: 3051886 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0082. Min Range: -5.0082
Max Act: 4.7582. Min Act: -0.1700
Data Index: 6099984 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0082. Min Range: -5.0082
Max Act: 4.7582. Min Act: -0.1700
Data Index: 8395197 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0082. Min Range: -5.0082
Max Act: 4.7270. Min Act: -0.1700
Data Index: 7603329 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0082. Min Range: -5.0082
Max Act: 4.7270. Min Act: -0.1700
Data Index: 3345199 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0082. Min Range: -5.0082
Max Act: 4.6957. Min Act: -0.1700
Data Index: 1627819 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0082. Min Range: -5.0082
Max Act: 4.6957. Min Act: -0.1700
Data Index: 1009404 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0082. Min Range: -5.0082
Max Act: 4.6957. Min Act: -0.1700
Data Index: 5366984 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0082. Min Range: -5.0082
Max Act: 4.6645. Min Act: -0.1700
Data Index: 5191437 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0082. Min Range: -5.0082
Max Act: 4.6332. Min Act: -0.1700
Data Index: 4893286 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0082. Min Range: -5.0082
Max Act: 4.6332. Min Act: -0.1700
Data Index: 999310 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0082. Min Range: -5.0082
Max Act: 4.6020. Min Act: -0.1700
Data Index: 2144911 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0082. Min Range: -5.0082
Max Act: 4.6020. Min Act: -0.1700
Data Index: 1258099 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0082. Min Range: -5.0082
Max Act: 4.6332. Min Act: -0.1700
Data Index: 8251096 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0082. Min Range: -5.0082
Max Act: 4.6020. Min Act: -0.1700
Data Index: 6279985 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0082. Min Range: -5.0082
Max Act: 4.6020. Min Act: -0.1700
Data Index: 7102660 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #19