Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4517 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5663. Min Range: -5.5663
Max Act: 5.5663. Min Act: -0.1700
Data Index: 5741752 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5663. Min Range: -5.5663
Max Act: 5.5663. Min Act: -0.1700
Data Index: 3383832 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5663. Min Range: -5.5663
Max Act: 5.4726. Min Act: -0.1700
Data Index: 6831736 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5663. Min Range: -5.5663
Max Act: 5.3788. Min Act: -0.1700
Data Index: 1799568 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5663. Min Range: -5.5663
Max Act: 5.3476. Min Act: -0.1700
Data Index: 1399085 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5663. Min Range: -5.5663
Max Act: 5.3163. Min Act: -0.1700
Data Index: 6294964 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5663. Min Range: -5.5663
Max Act: 5.2851. Min Act: -0.1700
Data Index: 4145167 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5663. Min Range: -5.5663
Max Act: 5.1288. Min Act: -0.1700
Data Index: 165456 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5663. Min Range: -5.5663
Max Act: 5.1601. Min Act: -0.1700
Data Index: 6901119 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5663. Min Range: -5.5663
Max Act: 5.1288. Min Act: -0.1700
Data Index: 7819521 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5663. Min Range: -5.5663
Max Act: 5.1288. Min Act: -0.1700
Data Index: 5317616 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5663. Min Range: -5.5663
Max Act: 5.1288. Min Act: -0.1700
Data Index: 3352900 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5663. Min Range: -5.5663
Max Act: 5.1288. Min Act: -0.1700
Data Index: 8702649 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5663. Min Range: -5.5663
Max Act: 5.1288. Min Act: -0.1700
Data Index: 6364513 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5663. Min Range: -5.5663
Max Act: 5.0976. Min Act: -0.1700
Data Index: 3532477 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5663. Min Range: -5.5663
Max Act: 5.0663. Min Act: -0.1700
Data Index: 6635417 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5663. Min Range: -5.5663
Max Act: 5.0663. Min Act: -0.1700
Data Index: 5510620 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5663. Min Range: -5.5663
Max Act: 5.0663. Min Act: -0.1700
Data Index: 8133910 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5663. Min Range: -5.5663
Max Act: 5.0351. Min Act: -0.1700
Data Index: 678614 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5663. Min Range: -5.5663
Max Act: 5.0663. Min Act: -0.1700
Data Index: 8571607 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #19