Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2258 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.4735. Min Range: -12.4735
Max Act: 12.4735. Min Act: -0.1700
Data Index: 7024975 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.4735. Min Range: -12.4735
Max Act: 12.2860. Min Act: -0.1700
Data Index: 8529436 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.4735. Min Range: -12.4735
Max Act: 12.2860. Min Act: -0.1700
Data Index: 7623183 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.4735. Min Range: -12.4735
Max Act: 12.1610. Min Act: -0.1700
Data Index: 193366 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.4735. Min Range: -12.4735
Max Act: 12.0360. Min Act: -0.1700
Data Index: 3931093 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.4735. Min Range: -12.4735
Max Act: 11.9735. Min Act: -0.1700
Data Index: 1643351 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.4735. Min Range: -12.4735
Max Act: 11.9110. Min Act: -0.1700
Data Index: 3483479 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.4735. Min Range: -12.4735
Max Act: 11.9110. Min Act: -0.1700
Data Index: 6268112 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.4735. Min Range: -12.4735
Max Act: 11.8485. Min Act: -0.1700
Data Index: 5952358 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.4735. Min Range: -12.4735
Max Act: 11.8485. Min Act: -0.1700
Data Index: 8320385 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.4735. Min Range: -12.4735
Max Act: 11.7860. Min Act: -0.1700
Data Index: 2645212 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.4735. Min Range: -12.4735
Max Act: 11.7860. Min Act: -0.1700
Data Index: 12941 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.4735. Min Range: -12.4735
Max Act: 11.7860. Min Act: -0.1700
Data Index: 8498218 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.4735. Min Range: -12.4735
Max Act: 11.7860. Min Act: -0.1700
Data Index: 6487037 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.4735. Min Range: -12.4735
Max Act: 11.8485. Min Act: -0.1700
Data Index: 5159024 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.4735. Min Range: -12.4735
Max Act: 11.7235. Min Act: -0.1700
Data Index: 1722382 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.4735. Min Range: -12.4735
Max Act: 11.7860. Min Act: -0.1700
Data Index: 917683 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.4735. Min Range: -12.4735
Max Act: 11.7235. Min Act: -0.1700
Data Index: 7233934 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.4735. Min Range: -12.4735
Max Act: 11.7235. Min Act: -0.1700
Data Index: 724394 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.4735. Min Range: -12.4735
Max Act: 11.7235. Min Act: -0.1700
Data Index: 778606 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #19