Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2231 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3893. Min Range: -9.3893
Max Act: 9.3893. Min Act: -0.1700
Data Index: 4712993 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3893. Min Range: -9.3893
Max Act: 9.2643. Min Act: -0.1700
Data Index: 2283418 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3893. Min Range: -9.3893
Max Act: 9.2643. Min Act: -0.1700
Data Index: 8044669 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3893. Min Range: -9.3893
Max Act: 9.2643. Min Act: -0.1700
Data Index: 4512560 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3893. Min Range: -9.3893
Max Act: 9.1393. Min Act: -0.1700
Data Index: 1113767 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3893. Min Range: -9.3893
Max Act: 9.0768. Min Act: -0.1700
Data Index: 8792937 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3893. Min Range: -9.3893
Max Act: 9.0143. Min Act: -0.1700
Data Index: 4575146 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3893. Min Range: -9.3893
Max Act: 9.0143. Min Act: -0.1700
Data Index: 7238603 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3893. Min Range: -9.3893
Max Act: 9.0143. Min Act: -0.1700
Data Index: 8202052 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3893. Min Range: -9.3893
Max Act: 8.9518. Min Act: -0.1700
Data Index: 8703828 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3893. Min Range: -9.3893
Max Act: 8.8893. Min Act: -0.1700
Data Index: 1522334 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3893. Min Range: -9.3893
Max Act: 8.8268. Min Act: -0.1700
Data Index: 6790471 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3893. Min Range: -9.3893
Max Act: 8.8893. Min Act: -0.1700
Data Index: 6143128 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3893. Min Range: -9.3893
Max Act: 8.7643. Min Act: -0.1700
Data Index: 6275243 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3893. Min Range: -9.3893
Max Act: 8.7643. Min Act: -0.1700
Data Index: 1160281 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3893. Min Range: -9.3893
Max Act: 8.7643. Min Act: -0.1700
Data Index: 3405200 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3893. Min Range: -9.3893
Max Act: 8.7018. Min Act: -0.1700
Data Index: 6272434 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3893. Min Range: -9.3893
Max Act: 8.7018. Min Act: -0.1700
Data Index: 3363284 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3893. Min Range: -9.3893
Max Act: 8.7018. Min Act: -0.1700
Data Index: 3485028 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3893. Min Range: -9.3893
Max Act: 8.6393. Min Act: -0.1700
Data Index: 7774621 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #19