Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1683 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1860. Min Range: -8.1860
Max Act: 8.1235. Min Act: -0.1700
Data Index: 3287108 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1860. Min Range: -8.1860
Max Act: 8.1860. Min Act: -0.1700
Data Index: 1940492 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1860. Min Range: -8.1860
Max Act: 8.0610. Min Act: -0.1700
Data Index: 7066911 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1860. Min Range: -8.1860
Max Act: 7.9985. Min Act: -0.1700
Data Index: 1784224 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1860. Min Range: -8.1860
Max Act: 7.9360. Min Act: -0.1700
Data Index: 5033967 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1860. Min Range: -8.1860
Max Act: 7.9360. Min Act: -0.1700
Data Index: 509396 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1860. Min Range: -8.1860
Max Act: 7.9360. Min Act: -0.1700
Data Index: 3691199 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1860. Min Range: -8.1860
Max Act: 7.9360. Min Act: -0.1700
Data Index: 2895617 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1860. Min Range: -8.1860
Max Act: 7.8735. Min Act: -0.1700
Data Index: 8438277 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1860. Min Range: -8.1860
Max Act: 7.8735. Min Act: -0.1700
Data Index: 1764670 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1860. Min Range: -8.1860
Max Act: 7.8735. Min Act: -0.1700
Data Index: 7903357 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1860. Min Range: -8.1860
Max Act: 7.8735. Min Act: -0.1700
Data Index: 5333091 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1860. Min Range: -8.1860
Max Act: 7.8735. Min Act: -0.1700
Data Index: 856441 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1860. Min Range: -8.1860
Max Act: 7.8735. Min Act: -0.1700
Data Index: 6907084 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1860. Min Range: -8.1860
Max Act: 7.8110. Min Act: -0.1700
Data Index: 1757536 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1860. Min Range: -8.1860
Max Act: 7.8110. Min Act: -0.1700
Data Index: 6099069 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1860. Min Range: -8.1860
Max Act: 7.7485. Min Act: -0.1700
Data Index: 541858 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1860. Min Range: -8.1860
Max Act: 7.8110. Min Act: -0.1700
Data Index: 3211202 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1860. Min Range: -8.1860
Max Act: 7.7485. Min Act: -0.1700
Data Index: 2830299 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1860. Min Range: -8.1860
Max Act: 7.8110. Min Act: -0.1700
Data Index: 7646139 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #19