Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6320 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8394. Min Range: -5.8394
Max Act: 5.8394. Min Act: -0.1700
Data Index: 5051763 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8394. Min Range: -5.8394
Max Act: 5.7769. Min Act: -0.1699
Data Index: 3023112 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8394. Min Range: -5.8394
Max Act: 5.6206. Min Act: -0.1700
Data Index: 605157 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8394. Min Range: -5.8394
Max Act: 5.5894. Min Act: -0.1700
Data Index: 4887315 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8394. Min Range: -5.8394
Max Act: 5.5581. Min Act: -0.1700
Data Index: 8113121 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8394. Min Range: -5.8394
Max Act: 5.5894. Min Act: -0.1700
Data Index: 4513136 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8394. Min Range: -5.8394
Max Act: 5.5894. Min Act: -0.1700
Data Index: 3064316 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8394. Min Range: -5.8394
Max Act: 5.5269. Min Act: -0.1700
Data Index: 2106160 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8394. Min Range: -5.8394
Max Act: 5.5269. Min Act: -0.1700
Data Index: 8190812 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8394. Min Range: -5.8394
Max Act: 5.5269. Min Act: -0.1700
Data Index: 4923126 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8394. Min Range: -5.8394
Max Act: 5.4956. Min Act: -0.1700
Data Index: 2393496 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8394. Min Range: -5.8394
Max Act: 5.4956. Min Act: -0.1700
Data Index: 5262800 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8394. Min Range: -5.8394
Max Act: 5.4956. Min Act: -0.1700
Data Index: 1162617 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8394. Min Range: -5.8394
Max Act: 5.4956. Min Act: -0.1700
Data Index: 1630998 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8394. Min Range: -5.8394
Max Act: 5.4956. Min Act: -0.1700
Data Index: 7131541 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8394. Min Range: -5.8394
Max Act: 5.4644. Min Act: -0.1699
Data Index: 580189 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8394. Min Range: -5.8394
Max Act: 5.4644. Min Act: -0.1700
Data Index: 107653 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8394. Min Range: -5.8394
Max Act: 5.4644. Min Act: -0.1700
Data Index: 5318278 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8394. Min Range: -5.8394
Max Act: 5.4644. Min Act: -0.1700
Data Index: 1638946 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8394. Min Range: -5.8394
Max Act: 5.4644. Min Act: -0.1700
Data Index: 4378766 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19