Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3684 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9651. Min Range: -5.9651
Max Act: 5.9651. Min Act: -0.1700
Data Index: 1244592 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9651. Min Range: -5.9651
Max Act: 5.8401. Min Act: -0.1700
Data Index: 1244591 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9651. Min Range: -5.9651
Max Act: 5.8088. Min Act: -0.1700
Data Index: 934823 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9651. Min Range: -5.9651
Max Act: 5.5588. Min Act: -0.1700
Data Index: 4287586 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9651. Min Range: -5.9651
Max Act: 5.5276. Min Act: -0.1700
Data Index: 8474589 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9651. Min Range: -5.9651
Max Act: 5.4651. Min Act: -0.1700
Data Index: 7883340 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9651. Min Range: -5.9651
Max Act: 5.4651. Min Act: -0.1700
Data Index: 1220595 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9651. Min Range: -5.9651
Max Act: 5.4026. Min Act: -0.1700
Data Index: 3064202 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9651. Min Range: -5.9651
Max Act: 5.4026. Min Act: -0.1700
Data Index: 7968240 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9651. Min Range: -5.9651
Max Act: 5.3713. Min Act: -0.1700
Data Index: 8306904 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9651. Min Range: -5.9651
Max Act: 5.3713. Min Act: -0.1700
Data Index: 7138842 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9651. Min Range: -5.9651
Max Act: 5.3401. Min Act: -0.1700
Data Index: 1693648 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9651. Min Range: -5.9651
Max Act: 5.3088. Min Act: -0.1700
Data Index: 7883351 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9651. Min Range: -5.9651
Max Act: 5.3401. Min Act: -0.1700
Data Index: 14400 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9651. Min Range: -5.9651
Max Act: 5.3401. Min Act: -0.1700
Data Index: 5484720 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9651. Min Range: -5.9651
Max Act: 5.3401. Min Act: -0.1700
Data Index: 4950413 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9651. Min Range: -5.9651
Max Act: 5.3088. Min Act: -0.1700
Data Index: 7549838 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9651. Min Range: -5.9651
Max Act: 5.3088. Min Act: -0.1700
Data Index: 6800705 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9651. Min Range: -5.9651
Max Act: 5.3401. Min Act: -0.1700
Data Index: 7883335 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9651. Min Range: -5.9651
Max Act: 5.2776. Min Act: -0.1700
Data Index: 3597730 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #19