Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1045 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8574. Min Range: -6.8574
Max Act: 6.8574. Min Act: -0.1700
Data Index: 1736021 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8574. Min Range: -6.8574
Max Act: 6.5136. Min Act: -0.1700
Data Index: 3082445 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8574. Min Range: -6.8574
Max Act: 6.3574. Min Act: -0.1700
Data Index: 3467380 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8574. Min Range: -6.8574
Max Act: 6.3574. Min Act: -0.1700
Data Index: 3342312 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8574. Min Range: -6.8574
Max Act: 6.2949. Min Act: -0.1700
Data Index: 5482058 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8574. Min Range: -6.8574
Max Act: 6.2949. Min Act: -0.1700
Data Index: 6174812 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8574. Min Range: -6.8574
Max Act: 6.2636. Min Act: -0.1700
Data Index: 2358381 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8574. Min Range: -6.8574
Max Act: 6.2011. Min Act: -0.1700
Data Index: 6808345 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8574. Min Range: -6.8574
Max Act: 6.1699. Min Act: -0.1700
Data Index: 7728835 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8574. Min Range: -6.8574
Max Act: 6.2011. Min Act: -0.1700
Data Index: 4044635 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8574. Min Range: -6.8574
Max Act: 6.1386. Min Act: -0.1700
Data Index: 299984 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8574. Min Range: -6.8574
Max Act: 6.1386. Min Act: -0.1700
Data Index: 6505541 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8574. Min Range: -6.8574
Max Act: 6.0761. Min Act: -0.1700
Data Index: 3606029 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8574. Min Range: -6.8574
Max Act: 6.0761. Min Act: -0.1700
Data Index: 4401930 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8574. Min Range: -6.8574
Max Act: 5.9824. Min Act: -0.1700
Data Index: 4314023 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8574. Min Range: -6.8574
Max Act: 6.0136. Min Act: -0.1700
Data Index: 4866603 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8574. Min Range: -6.8574
Max Act: 6.0136. Min Act: -0.1700
Data Index: 6261682 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8574. Min Range: -6.8574
Max Act: 6.0449. Min Act: -0.1700
Data Index: 2012281 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8574. Min Range: -6.8574
Max Act: 6.0136. Min Act: -0.1700
Data Index: 3312144 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8574. Min Range: -6.8574
Max Act: 5.9824. Min Act: -0.1700
Data Index: 6521503 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #19