Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4324 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1943. Min Range: -8.1943
Max Act: 8.1943. Min Act: -0.1700
Data Index: 3709904 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1943. Min Range: -8.1943
Max Act: 7.8506. Min Act: -0.1699
Data Index: 168811 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1943. Min Range: -8.1943
Max Act: 7.6318. Min Act: -0.1700
Data Index: 3985326 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1943. Min Range: -8.1943
Max Act: 7.6631. Min Act: -0.1700
Data Index: 4367410 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1943. Min Range: -8.1943
Max Act: 7.6318. Min Act: -0.1700
Data Index: 2315549 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1943. Min Range: -8.1943
Max Act: 7.5693. Min Act: -0.1700
Data Index: 885335 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1943. Min Range: -8.1943
Max Act: 7.5381. Min Act: -0.1700
Data Index: 2298815 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1943. Min Range: -8.1943
Max Act: 7.4443. Min Act: -0.1700
Data Index: 7798661 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1943. Min Range: -8.1943
Max Act: 7.4131. Min Act: -0.1694
Data Index: 168804 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1943. Min Range: -8.1943
Max Act: 7.4131. Min Act: -0.1697
Data Index: 2732553 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1943. Min Range: -8.1943
Max Act: 7.4131. Min Act: -0.1700
Data Index: 6250270 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1943. Min Range: -8.1943
Max Act: 7.3818. Min Act: -0.1700
Data Index: 5146883 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1943. Min Range: -8.1943
Max Act: 7.3506. Min Act: -0.1700
Data Index: 4427783 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1943. Min Range: -8.1943
Max Act: 7.3506. Min Act: -0.1700
Data Index: 7877441 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1943. Min Range: -8.1943
Max Act: 7.3193. Min Act: -0.1700
Data Index: 3229643 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1943. Min Range: -8.1943
Max Act: 7.3193. Min Act: -0.1700
Data Index: 3486876 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1943. Min Range: -8.1943
Max Act: 7.3193. Min Act: -0.1700
Data Index: 5822708 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1943. Min Range: -8.1943
Max Act: 7.3193. Min Act: -0.1700
Data Index: 7514685 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1943. Min Range: -8.1943
Max Act: 7.3193. Min Act: -0.1700
Data Index: 6463718 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1943. Min Range: -8.1943
Max Act: 7.2881. Min Act: -0.1700
Data Index: 2285202 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #19