Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1106 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6775. Min Range: -3.6775
Max Act: 3.6775. Min Act: -0.1700
Data Index: 4963627 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6775. Min Range: -3.6775
Max Act: 3.4427. Min Act: -0.1700
Data Index: 8170653 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6775. Min Range: -3.6775
Max Act: 3.4427. Min Act: -0.1700
Data Index: 4345929 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6775. Min Range: -3.6775
Max Act: 3.4113. Min Act: -0.1700
Data Index: 3038015 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6775. Min Range: -3.6775
Max Act: 3.4270. Min Act: -0.1700
Data Index: 3053881 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6775. Min Range: -3.6775
Max Act: 3.3957. Min Act: -0.1700
Data Index: 691192 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6775. Min Range: -3.6775
Max Act: 3.3957. Min Act: -0.1700
Data Index: 1366983 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6775. Min Range: -3.6775
Max Act: 3.3957. Min Act: -0.1700
Data Index: 8135713 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6775. Min Range: -3.6775
Max Act: 3.3800. Min Act: -0.1700
Data Index: 5295695 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6775. Min Range: -3.6775
Max Act: 3.3486. Min Act: -0.1700
Data Index: 6590427 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6775. Min Range: -3.6775
Max Act: 3.3329. Min Act: -0.1700
Data Index: 1092354 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6775. Min Range: -3.6775
Max Act: 3.3486. Min Act: -0.1700
Data Index: 2927869 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6775. Min Range: -3.6775
Max Act: 3.3172. Min Act: -0.1700
Data Index: 1304690 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6775. Min Range: -3.6775
Max Act: 3.3015. Min Act: -0.1700
Data Index: 853872 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6775. Min Range: -3.6775
Max Act: 3.3172. Min Act: -0.1700
Data Index: 1318655 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6775. Min Range: -3.6775
Max Act: 3.3015. Min Act: -0.1700
Data Index: 7311964 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6775. Min Range: -3.6775
Max Act: 3.3015. Min Act: -0.1700
Data Index: 4894854 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6775. Min Range: -3.6775
Max Act: 3.3015. Min Act: -0.1700
Data Index: 6207016 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6775. Min Range: -3.6775
Max Act: 3.3015. Min Act: -0.1700
Data Index: 5894732 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6775. Min Range: -3.6775
Max Act: 3.3015. Min Act: -0.1700
Data Index: 3228492 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #19