Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1014 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7445. Min Range: -4.7445
Max Act: 4.7445. Min Act: -0.1700
Data Index: 946158 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7445. Min Range: -4.7445
Max Act: 4.7445. Min Act: -0.1700
Data Index: 6902663 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7445. Min Range: -4.7445
Max Act: 4.6508. Min Act: -0.1700
Data Index: 2387193 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7445. Min Range: -4.7445
Max Act: 4.6195. Min Act: -0.1700
Data Index: 970325 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7445. Min Range: -4.7445
Max Act: 4.5883. Min Act: -0.1700
Data Index: 995651 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7445. Min Range: -4.7445
Max Act: 4.5883. Min Act: -0.1700
Data Index: 1079918 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7445. Min Range: -4.7445
Max Act: 4.5883. Min Act: -0.1700
Data Index: 4135142 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7445. Min Range: -4.7445
Max Act: 4.5570. Min Act: -0.1700
Data Index: 6156328 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7445. Min Range: -4.7445
Max Act: 4.6195. Min Act: -0.1700
Data Index: 27623 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7445. Min Range: -4.7445
Max Act: 4.5570. Min Act: -0.1700
Data Index: 8694798 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7445. Min Range: -4.7445
Max Act: 4.5570. Min Act: -0.1700
Data Index: 2926816 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7445. Min Range: -4.7445
Max Act: 4.5570. Min Act: -0.1700
Data Index: 5467229 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7445. Min Range: -4.7445
Max Act: 4.5570. Min Act: -0.1700
Data Index: 8312141 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7445. Min Range: -4.7445
Max Act: 4.5258. Min Act: -0.1700
Data Index: 5472440 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7445. Min Range: -4.7445
Max Act: 4.5570. Min Act: -0.1700
Data Index: 4454727 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7445. Min Range: -4.7445
Max Act: 4.5258. Min Act: -0.1700
Data Index: 8356582 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7445. Min Range: -4.7445
Max Act: 4.5258. Min Act: -0.1700
Data Index: 3196566 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7445. Min Range: -4.7445
Max Act: 4.5258. Min Act: -0.1700
Data Index: 7420720 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7445. Min Range: -4.7445
Max Act: 4.4945. Min Act: -0.1700
Data Index: 6173822 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7445. Min Range: -4.7445
Max Act: 4.4945. Min Act: -0.1700
Data Index: 6177310 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #19