Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2864 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.5310. Min Range: -7.5310
Max Act: 7.5310. Min Act: -0.1700
Data Index: 1083417 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5310. Min Range: -7.5310
Max Act: 7.3435. Min Act: -0.1700
Data Index: 7448929 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5310. Min Range: -7.5310
Max Act: 7.2810. Min Act: -0.1700
Data Index: 7037871 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5310. Min Range: -7.5310
Max Act: 7.0935. Min Act: -0.1700
Data Index: 3843422 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5310. Min Range: -7.5310
Max Act: 6.9372. Min Act: -0.1700
Data Index: 1724635 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5310. Min Range: -7.5310
Max Act: 6.7810. Min Act: -0.1700
Data Index: 3125231 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5310. Min Range: -7.5310
Max Act: 6.7497. Min Act: -0.1700
Data Index: 7475080 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5310. Min Range: -7.5310
Max Act: 6.8122. Min Act: -0.1700
Data Index: 5839664 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5310. Min Range: -7.5310
Max Act: 6.7497. Min Act: -0.1700
Data Index: 4385269 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5310. Min Range: -7.5310
Max Act: 6.7185. Min Act: -0.1700
Data Index: 39217 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5310. Min Range: -7.5310
Max Act: 6.6872. Min Act: -0.1700
Data Index: 2560993 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5310. Min Range: -7.5310
Max Act: 6.7185. Min Act: -0.1700
Data Index: 2571303 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5310. Min Range: -7.5310
Max Act: 6.6560. Min Act: -0.1700
Data Index: 5242416 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5310. Min Range: -7.5310
Max Act: 6.5935. Min Act: -0.1700
Data Index: 999438 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5310. Min Range: -7.5310
Max Act: 6.5935. Min Act: -0.1700
Data Index: 3088722 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5310. Min Range: -7.5310
Max Act: 6.6247. Min Act: -0.1700
Data Index: 5327262 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5310. Min Range: -7.5310
Max Act: 6.4685. Min Act: -0.1700
Data Index: 6052381 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5310. Min Range: -7.5310
Max Act: 6.4997. Min Act: -0.1700
Data Index: 6469066 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5310. Min Range: -7.5310
Max Act: 6.4997. Min Act: -0.1700
Data Index: 3196555 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5310. Min Range: -7.5310
Max Act: 6.4685. Min Act: -0.1700
Data Index: 3781989 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #19