Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1904 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.7957. Min Range: -7.7957
Max Act: 7.7957. Min Act: -0.1700
Data Index: 4810013 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7957. Min Range: -7.7957
Max Act: 7.3895. Min Act: -0.1700
Data Index: 2406686 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7957. Min Range: -7.7957
Max Act: 7.2957. Min Act: -0.1700
Data Index: 4150739 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7957. Min Range: -7.7957
Max Act: 7.2332. Min Act: -0.1700
Data Index: 5114589 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7957. Min Range: -7.7957
Max Act: 6.9832. Min Act: -0.1700
Data Index: 1805133 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7957. Min Range: -7.7957
Max Act: 6.9520. Min Act: -0.1700
Data Index: 1243942 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7957. Min Range: -7.7957
Max Act: 6.9520. Min Act: -0.1700
Data Index: 1327181 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7957. Min Range: -7.7957
Max Act: 6.7957. Min Act: -0.1700
Data Index: 5161237 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7957. Min Range: -7.7957
Max Act: 6.7957. Min Act: -0.1700
Data Index: 2547424 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7957. Min Range: -7.7957
Max Act: 6.8270. Min Act: -0.1700
Data Index: 4184526 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7957. Min Range: -7.7957
Max Act: 6.7957. Min Act: -0.1700
Data Index: 7160817 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7957. Min Range: -7.7957
Max Act: 6.7645. Min Act: -0.1700
Data Index: 1127179 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7957. Min Range: -7.7957
Max Act: 6.7645. Min Act: -0.1700
Data Index: 724263 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7957. Min Range: -7.7957
Max Act: 6.7957. Min Act: -0.1700
Data Index: 6779819 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7957. Min Range: -7.7957
Max Act: 6.7332. Min Act: -0.1700
Data Index: 7334995 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7957. Min Range: -7.7957
Max Act: 6.7332. Min Act: -0.1700
Data Index: 6058887 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7957. Min Range: -7.7957
Max Act: 6.7332. Min Act: -0.1700
Data Index: 7250924 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7957. Min Range: -7.7957
Max Act: 6.7020. Min Act: -0.1700
Data Index: 1779282 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7957. Min Range: -7.7957
Max Act: 6.6082. Min Act: -0.1700
Data Index: 945169 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7957. Min Range: -7.7957
Max Act: 6.6707. Min Act: -0.1700
Data Index: 6750379 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #19