Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 108 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8520. Min Range: -6.8520
Max Act: 6.8520. Min Act: -0.1700
Data Index: 8164239 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8520. Min Range: -6.8520
Max Act: 6.7270. Min Act: -0.1700
Data Index: 6490006 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8520. Min Range: -6.8520
Max Act: 6.6332. Min Act: -0.1700
Data Index: 6591573 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8520. Min Range: -6.8520
Max Act: 6.6645. Min Act: -0.1700
Data Index: 8102645 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8520. Min Range: -6.8520
Max Act: 6.6332. Min Act: -0.1700
Data Index: 2684270 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8520. Min Range: -6.8520
Max Act: 6.6020. Min Act: -0.1700
Data Index: 3497597 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8520. Min Range: -6.8520
Max Act: 6.6020. Min Act: -0.1700
Data Index: 2370100 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8520. Min Range: -6.8520
Max Act: 6.6020. Min Act: -0.1700
Data Index: 1208993 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8520. Min Range: -6.8520
Max Act: 6.6020. Min Act: -0.1700
Data Index: 7885012 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8520. Min Range: -6.8520
Max Act: 6.5395. Min Act: -0.1700
Data Index: 850604 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8520. Min Range: -6.8520
Max Act: 6.5082. Min Act: -0.1700
Data Index: 4373485 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8520. Min Range: -6.8520
Max Act: 6.5082. Min Act: -0.1700
Data Index: 6724323 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8520. Min Range: -6.8520
Max Act: 6.5082. Min Act: -0.1700
Data Index: 1697560 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8520. Min Range: -6.8520
Max Act: 6.4770. Min Act: -0.1700
Data Index: 2676455 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8520. Min Range: -6.8520
Max Act: 6.4770. Min Act: -0.1700
Data Index: 7416075 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8520. Min Range: -6.8520
Max Act: 6.4457. Min Act: -0.1700
Data Index: 8638441 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8520. Min Range: -6.8520
Max Act: 6.4770. Min Act: -0.1700
Data Index: 880790 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8520. Min Range: -6.8520
Max Act: 6.4457. Min Act: -0.1700
Data Index: 7224390 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8520. Min Range: -6.8520
Max Act: 6.4145. Min Act: -0.1700
Data Index: 594986 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8520. Min Range: -6.8520
Max Act: 6.4457. Min Act: -0.1700
Data Index: 7655145 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #19