Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 346 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1943. Min Range: -5.1943
Max Act: 5.1943. Min Act: -0.1700
Data Index: 183848 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1943. Min Range: -5.1943
Max Act: 4.9131. Min Act: -0.1700
Data Index: 7391200 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1943. Min Range: -5.1943
Max Act: 4.9131. Min Act: -0.1700
Data Index: 2229806 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1943. Min Range: -5.1943
Max Act: 4.9131. Min Act: -0.1700
Data Index: 8604307 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1943. Min Range: -5.1943
Max Act: 4.8506. Min Act: -0.1700
Data Index: 2912093 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1943. Min Range: -5.1943
Max Act: 4.8193. Min Act: -0.1700
Data Index: 8809569 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1943. Min Range: -5.1943
Max Act: 4.7881. Min Act: -0.1700
Data Index: 5794609 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1943. Min Range: -5.1943
Max Act: 4.7568. Min Act: -0.1700
Data Index: 2776437 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1943. Min Range: -5.1943
Max Act: 4.7256. Min Act: -0.1700
Data Index: 5834351 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1943. Min Range: -5.1943
Max Act: 4.7256. Min Act: -0.1700
Data Index: 994123 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1943. Min Range: -5.1943
Max Act: 4.6943. Min Act: -0.1700
Data Index: 2014116 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1943. Min Range: -5.1943
Max Act: 4.6631. Min Act: -0.1700
Data Index: 2930727 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1943. Min Range: -5.1943
Max Act: 4.6631. Min Act: -0.1700
Data Index: 8178971 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1943. Min Range: -5.1943
Max Act: 4.6631. Min Act: -0.1700
Data Index: 3558912 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1943. Min Range: -5.1943
Max Act: 4.6631. Min Act: -0.1700
Data Index: 5089020 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1943. Min Range: -5.1943
Max Act: 4.6318. Min Act: -0.1700
Data Index: 5465180 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1943. Min Range: -5.1943
Max Act: 4.6318. Min Act: -0.1700
Data Index: 703055 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1943. Min Range: -5.1943
Max Act: 4.6318. Min Act: -0.1700
Data Index: 8830573 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1943. Min Range: -5.1943
Max Act: 4.6318. Min Act: -0.1700
Data Index: 8096163 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1943. Min Range: -5.1943
Max Act: 4.6006. Min Act: -0.1700
Data Index: 4884670 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #19