Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 45 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1140. Min Range: -6.1140
Max Act: 6.1140. Min Act: -0.1700
Data Index: 4970036 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1140. Min Range: -6.1140
Max Act: 6.0827. Min Act: -0.1700
Data Index: 95075 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1140. Min Range: -6.1140
Max Act: 6.0202. Min Act: -0.1700
Data Index: 8788869 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1140. Min Range: -6.1140
Max Act: 5.9890. Min Act: -0.1700
Data Index: 1094092 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1140. Min Range: -6.1140
Max Act: 5.9265. Min Act: -0.1700
Data Index: 1783701 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1140. Min Range: -6.1140
Max Act: 5.8952. Min Act: -0.1700
Data Index: 3092489 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1140. Min Range: -6.1140
Max Act: 5.8640. Min Act: -0.1700
Data Index: 3544878 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1140. Min Range: -6.1140
Max Act: 5.8640. Min Act: -0.1700
Data Index: 1685345 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1140. Min Range: -6.1140
Max Act: 5.8640. Min Act: -0.1700
Data Index: 3261709 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1140. Min Range: -6.1140
Max Act: 5.8327. Min Act: -0.1700
Data Index: 4477249 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1140. Min Range: -6.1140
Max Act: 5.8327. Min Act: -0.1700
Data Index: 4406911 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1140. Min Range: -6.1140
Max Act: 5.8327. Min Act: -0.1700
Data Index: 4622410 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1140. Min Range: -6.1140
Max Act: 5.8327. Min Act: -0.1700
Data Index: 3035158 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1140. Min Range: -6.1140
Max Act: 5.8015. Min Act: -0.1700
Data Index: 2121398 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1140. Min Range: -6.1140
Max Act: 5.7702. Min Act: -0.1700
Data Index: 4406904 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1140. Min Range: -6.1140
Max Act: 5.7390. Min Act: -0.1700
Data Index: 4362347 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1140. Min Range: -6.1140
Max Act: 5.7077. Min Act: -0.1700
Data Index: 1699567 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1140. Min Range: -6.1140
Max Act: 5.7390. Min Act: -0.1700
Data Index: 6823961 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1140. Min Range: -6.1140
Max Act: 5.7077. Min Act: -0.1700
Data Index: 840601 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1140. Min Range: -6.1140
Max Act: 5.7077. Min Act: -0.1700
Data Index: 1458137 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #19