Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5670 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7586. Min Range: -5.7586
Max Act: 5.7586. Min Act: -0.1700
Data Index: 3604107 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7586. Min Range: -5.7586
Max Act: 5.6024. Min Act: -0.1700
Data Index: 5888929 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7586. Min Range: -5.7586
Max Act: 5.6024. Min Act: -0.1700
Data Index: 5286957 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7586. Min Range: -5.7586
Max Act: 5.5399. Min Act: -0.1700
Data Index: 4289492 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7586. Min Range: -5.7586
Max Act: 5.4149. Min Act: -0.1700
Data Index: 2213718 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7586. Min Range: -5.7586
Max Act: 5.4149. Min Act: -0.1700
Data Index: 6742271 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7586. Min Range: -5.7586
Max Act: 5.4149. Min Act: -0.1700
Data Index: 4954727 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7586. Min Range: -5.7586
Max Act: 5.3211. Min Act: -0.1700
Data Index: 8407878 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7586. Min Range: -5.7586
Max Act: 5.3211. Min Act: -0.1700
Data Index: 3090784 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7586. Min Range: -5.7586
Max Act: 5.3211. Min Act: -0.1700
Data Index: 65677 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7586. Min Range: -5.7586
Max Act: 5.2899. Min Act: -0.1700
Data Index: 844656 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7586. Min Range: -5.7586
Max Act: 5.2586. Min Act: -0.1700
Data Index: 4530137 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7586. Min Range: -5.7586
Max Act: 5.2274. Min Act: -0.1700
Data Index: 5343131 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7586. Min Range: -5.7586
Max Act: 5.2274. Min Act: -0.1700
Data Index: 5015254 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7586. Min Range: -5.7586
Max Act: 5.2274. Min Act: -0.1700
Data Index: 2147919 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7586. Min Range: -5.7586
Max Act: 5.1961. Min Act: -0.1700
Data Index: 4288618 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7586. Min Range: -5.7586
Max Act: 5.2274. Min Act: -0.1700
Data Index: 329086 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7586. Min Range: -5.7586
Max Act: 5.1961. Min Act: -0.1700
Data Index: 6691069 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7586. Min Range: -5.7586
Max Act: 5.1961. Min Act: -0.1700
Data Index: 5664454 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7586. Min Range: -5.7586
Max Act: 5.1649. Min Act: -0.1700
Data Index: 5931913 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #19