Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 8 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.9825. Min Range: -6.9825
Max Act: 6.9825. Min Act: -0.1700
Data Index: 7880636 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9825. Min Range: -6.9825
Max Act: 6.8262. Min Act: -0.1700
Data Index: 4813108 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9825. Min Range: -6.9825
Max Act: 6.8575. Min Act: -0.1700
Data Index: 7177878 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9825. Min Range: -6.9825
Max Act: 6.7950. Min Act: -0.1700
Data Index: 5829221 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9825. Min Range: -6.9825
Max Act: 6.7950. Min Act: -0.1700
Data Index: 6098414 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9825. Min Range: -6.9825
Max Act: 6.7637. Min Act: -0.1700
Data Index: 3932416 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9825. Min Range: -6.9825
Max Act: 6.7325. Min Act: -0.1700
Data Index: 6628057 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9825. Min Range: -6.9825
Max Act: 6.7012. Min Act: -0.1700
Data Index: 3932412 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9825. Min Range: -6.9825
Max Act: 6.6700. Min Act: -0.1700
Data Index: 1352261 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9825. Min Range: -6.9825
Max Act: 6.6700. Min Act: -0.1700
Data Index: 3284262 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9825. Min Range: -6.9825
Max Act: 6.6387. Min Act: -0.1700
Data Index: 1314437 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9825. Min Range: -6.9825
Max Act: 6.6387. Min Act: -0.1700
Data Index: 1497179 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9825. Min Range: -6.9825
Max Act: 6.6075. Min Act: -0.1700
Data Index: 756754 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9825. Min Range: -6.9825
Max Act: 6.5762. Min Act: -0.1700
Data Index: 8181708 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9825. Min Range: -6.9825
Max Act: 6.5762. Min Act: -0.1700
Data Index: 6628056 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9825. Min Range: -6.9825
Max Act: 6.5450. Min Act: -0.1700
Data Index: 2992059 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9825. Min Range: -6.9825
Max Act: 6.5762. Min Act: -0.1700
Data Index: 7466894 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9825. Min Range: -6.9825
Max Act: 6.4825. Min Act: -0.1700
Data Index: 2038350 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9825. Min Range: -6.9825
Max Act: 6.5137. Min Act: -0.1700
Data Index: 2496572 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9825. Min Range: -6.9825
Max Act: 6.5137. Min Act: -0.1700
Data Index: 6883975 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #19