Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3136 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0235. Min Range: -5.0235
Max Act: 5.0235. Min Act: -0.1700
Data Index: 18758 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0235. Min Range: -5.0235
Max Act: 4.8985. Min Act: -0.1700
Data Index: 7700843 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0235. Min Range: -5.0235
Max Act: 4.7423. Min Act: -0.1700
Data Index: 3621136 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0235. Min Range: -5.0235
Max Act: 4.7110. Min Act: -0.1700
Data Index: 7206473 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0235. Min Range: -5.0235
Max Act: 4.7110. Min Act: -0.1700
Data Index: 368163 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0235. Min Range: -5.0235
Max Act: 4.6798. Min Act: -0.1700
Data Index: 1771593 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0235. Min Range: -5.0235
Max Act: 4.6173. Min Act: -0.1700
Data Index: 2553971 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0235. Min Range: -5.0235
Max Act: 4.6485. Min Act: -0.1700
Data Index: 7700847 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0235. Min Range: -5.0235
Max Act: 4.6485. Min Act: -0.1700
Data Index: 2820681 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0235. Min Range: -5.0235
Max Act: 4.6485. Min Act: -0.1700
Data Index: 3081127 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0235. Min Range: -5.0235
Max Act: 4.6485. Min Act: -0.1700
Data Index: 4958164 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0235. Min Range: -5.0235
Max Act: 4.6173. Min Act: -0.1700
Data Index: 4845885 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0235. Min Range: -5.0235
Max Act: 4.6173. Min Act: -0.1700
Data Index: 3348986 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0235. Min Range: -5.0235
Max Act: 4.6173. Min Act: -0.1700
Data Index: 3661709 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0235. Min Range: -5.0235
Max Act: 4.6173. Min Act: -0.1700
Data Index: 6320 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0235. Min Range: -5.0235
Max Act: 4.6173. Min Act: -0.1700
Data Index: 2731401 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0235. Min Range: -5.0235
Max Act: 4.6173. Min Act: -0.1700
Data Index: 3741571 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0235. Min Range: -5.0235
Max Act: 4.5548. Min Act: -0.1700
Data Index: 6067498 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0235. Min Range: -5.0235
Max Act: 4.5860. Min Act: -0.1700
Data Index: 3253368 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0235. Min Range: -5.0235
Max Act: 4.5860. Min Act: -0.1700
Data Index: 632783 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #19