Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4053 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2988. Min Range: -3.2988
Max Act: 3.2831. Min Act: -0.1700
Data Index: 8669980 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2988. Min Range: -3.2988
Max Act: 3.2988. Min Act: -0.1700
Data Index: 6173288 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2988. Min Range: -3.2988
Max Act: 3.2674. Min Act: -0.1700
Data Index: 1311162 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2988. Min Range: -3.2988
Max Act: 3.2517. Min Act: -0.1700
Data Index: 7976075 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2988. Min Range: -3.2988
Max Act: 3.2360. Min Act: -0.1700
Data Index: 6173289 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2988. Min Range: -3.2988
Max Act: 3.2674. Min Act: -0.1700
Data Index: 854721 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2988. Min Range: -3.2988
Max Act: 3.2046. Min Act: -0.1700
Data Index: 8084931 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2988. Min Range: -3.2988
Max Act: 3.1888. Min Act: -0.1700
Data Index: 8669977 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2988. Min Range: -3.2988
Max Act: 3.1731. Min Act: -0.1700
Data Index: 6173292 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2988. Min Range: -3.2988
Max Act: 3.1259. Min Act: -0.1700
Data Index: 6967389 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2988. Min Range: -3.2988
Max Act: 3.1416. Min Act: -0.1700
Data Index: 8536 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2988. Min Range: -3.2988
Max Act: 3.1416. Min Act: -0.1700
Data Index: 8669978 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2988. Min Range: -3.2988
Max Act: 3.1259. Min Act: -0.1700
Data Index: 8669979 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2988. Min Range: -3.2988
Max Act: 3.1101. Min Act: -0.1700
Data Index: 3074653 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2988. Min Range: -3.2988
Max Act: 3.1101. Min Act: -0.1700
Data Index: 6243744 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2988. Min Range: -3.2988
Max Act: 3.1259. Min Act: -0.1700
Data Index: 8040910 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2988. Min Range: -3.2988
Max Act: 3.0944. Min Act: -0.1700
Data Index: 5813384 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2988. Min Range: -3.2988
Max Act: 3.0944. Min Act: -0.1700
Data Index: 4631627 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2988. Min Range: -3.2988
Max Act: 3.0944. Min Act: -0.1700
Data Index: 1717571 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2988. Min Range: -3.2988
Max Act: 3.0628. Min Act: -0.1700
Data Index: 1355479 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #19