Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3483 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6966. Min Range: -3.6966
Max Act: 3.6966. Min Act: -0.1700
Data Index: 7728547 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6966. Min Range: -3.6966
Max Act: 3.6653. Min Act: -0.1700
Data Index: 1286361 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6966. Min Range: -3.6966
Max Act: 3.4932. Min Act: -0.1700
Data Index: 6118105 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6966. Min Range: -3.6966
Max Act: 3.4775. Min Act: -0.1700
Data Index: 4892351 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6966. Min Range: -3.6966
Max Act: 3.4462. Min Act: -0.1700
Data Index: 4696373 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6966. Min Range: -3.6966
Max Act: 3.4148. Min Act: -0.1700
Data Index: 4474656 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6966. Min Range: -3.6966
Max Act: 3.4148. Min Act: -0.1700
Data Index: 7743217 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6966. Min Range: -3.6966
Max Act: 3.4148. Min Act: -0.1700
Data Index: 415037 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6966. Min Range: -3.6966
Max Act: 3.4305. Min Act: -0.1700
Data Index: 406435 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6966. Min Range: -3.6966
Max Act: 3.3835. Min Act: -0.1700
Data Index: 1247608 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6966. Min Range: -3.6966
Max Act: 3.3991. Min Act: -0.1700
Data Index: 8571656 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6966. Min Range: -3.6966
Max Act: 3.4148. Min Act: -0.1700
Data Index: 963128 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6966. Min Range: -3.6966
Max Act: 3.3678. Min Act: -0.1700
Data Index: 7262626 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6966. Min Range: -3.6966
Max Act: 3.3835. Min Act: -0.1700
Data Index: 6634175 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6966. Min Range: -3.6966
Max Act: 3.3521. Min Act: -0.1700
Data Index: 3463687 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6966. Min Range: -3.6966
Max Act: 3.3521. Min Act: -0.1700
Data Index: 952808 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6966. Min Range: -3.6966
Max Act: 3.3364. Min Act: -0.1700
Data Index: 5988246 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6966. Min Range: -3.6966
Max Act: 3.3364. Min Act: -0.1700
Data Index: 506794 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6966. Min Range: -3.6966
Max Act: 3.2893. Min Act: -0.1700
Data Index: 7243661 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6966. Min Range: -3.6966
Max Act: 3.3207. Min Act: -0.1700
Data Index: 4455264 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #19