Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5238 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3911. Min Range: -7.3911
Max Act: 7.3911. Min Act: -0.1700
Data Index: 1808071 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3911. Min Range: -7.3911
Max Act: 7.2349. Min Act: -0.1700
Data Index: 8133720 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3911. Min Range: -7.3911
Max Act: 7.2036. Min Act: -0.1700
Data Index: 6515675 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3911. Min Range: -7.3911
Max Act: 7.0786. Min Act: -0.1700
Data Index: 85840 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3911. Min Range: -7.3911
Max Act: 7.0786. Min Act: -0.1700
Data Index: 8040207 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3911. Min Range: -7.3911
Max Act: 6.8911. Min Act: -0.1700
Data Index: 4282333 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3911. Min Range: -7.3911
Max Act: 6.9224. Min Act: -0.1700
Data Index: 5728709 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3911. Min Range: -7.3911
Max Act: 6.8599. Min Act: -0.1700
Data Index: 3601701 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3911. Min Range: -7.3911
Max Act: 6.8286. Min Act: -0.1700
Data Index: 467886 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3911. Min Range: -7.3911
Max Act: 6.7974. Min Act: -0.1700
Data Index: 5357036 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3911. Min Range: -7.3911
Max Act: 6.7974. Min Act: -0.1700
Data Index: 3553646 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3911. Min Range: -7.3911
Max Act: 6.7974. Min Act: -0.1700
Data Index: 1679145 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3911. Min Range: -7.3911
Max Act: 6.7661. Min Act: -0.1700
Data Index: 6119436 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3911. Min Range: -7.3911
Max Act: 6.7661. Min Act: -0.1700
Data Index: 1998238 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3911. Min Range: -7.3911
Max Act: 6.7661. Min Act: -0.1700
Data Index: 4635490 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3911. Min Range: -7.3911
Max Act: 6.7349. Min Act: -0.1700
Data Index: 6021951 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3911. Min Range: -7.3911
Max Act: 6.7349. Min Act: -0.1700
Data Index: 2325445 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3911. Min Range: -7.3911
Max Act: 6.7036. Min Act: -0.1700
Data Index: 628625 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3911. Min Range: -7.3911
Max Act: 6.6724. Min Act: -0.1700
Data Index: 5905583 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3911. Min Range: -7.3911
Max Act: 6.6724. Min Act: -0.1700
Data Index: 7582216 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #19