Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4808 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3202. Min Range: -7.3202
Max Act: 7.3202. Min Act: -0.1700
Data Index: 3230733 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3202. Min Range: -7.3202
Max Act: 7.1327. Min Act: -0.1700
Data Index: 3230732 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3202. Min Range: -7.3202
Max Act: 7.0390. Min Act: -0.1700
Data Index: 4043595 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3202. Min Range: -7.3202
Max Act: 6.9140. Min Act: -0.1700
Data Index: 5245043 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3202. Min Range: -7.3202
Max Act: 6.8827. Min Act: -0.1700
Data Index: 6997211 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3202. Min Range: -7.3202
Max Act: 6.8515. Min Act: -0.1700
Data Index: 1140054 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3202. Min Range: -7.3202
Max Act: 6.7890. Min Act: -0.1700
Data Index: 8731916 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3202. Min Range: -7.3202
Max Act: 6.7890. Min Act: -0.1700
Data Index: 786820 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3202. Min Range: -7.3202
Max Act: 6.7577. Min Act: -0.1700
Data Index: 7070248 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3202. Min Range: -7.3202
Max Act: 6.7265. Min Act: -0.1700
Data Index: 6358962 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3202. Min Range: -7.3202
Max Act: 6.6640. Min Act: -0.1700
Data Index: 8528580 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3202. Min Range: -7.3202
Max Act: 6.6327. Min Act: -0.1700
Data Index: 3033567 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3202. Min Range: -7.3202
Max Act: 6.6327. Min Act: -0.1700
Data Index: 1305615 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3202. Min Range: -7.3202
Max Act: 6.6015. Min Act: -0.1700
Data Index: 6756821 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3202. Min Range: -7.3202
Max Act: 6.5702. Min Act: -0.1700
Data Index: 8356274 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3202. Min Range: -7.3202
Max Act: 6.5390. Min Act: -0.1700
Data Index: 6690888 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3202. Min Range: -7.3202
Max Act: 6.5702. Min Act: -0.1700
Data Index: 5609760 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3202. Min Range: -7.3202
Max Act: 6.5390. Min Act: -0.1700
Data Index: 4019758 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3202. Min Range: -7.3202
Max Act: 6.5077. Min Act: -0.1700
Data Index: 4930512 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3202. Min Range: -7.3202
Max Act: 6.5390. Min Act: -0.1700
Data Index: 7247286 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #19