Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 442 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.5343. Min Range: -6.5343
Max Act: 6.5343. Min Act: -0.1700
Data Index: 6198713 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5343. Min Range: -6.5343
Max Act: 6.2843. Min Act: -0.1700
Data Index: 5387326 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5343. Min Range: -6.5343
Max Act: 6.2531. Min Act: -0.1700
Data Index: 3370851 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5343. Min Range: -6.5343
Max Act: 6.2218. Min Act: -0.1700
Data Index: 3137937 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5343. Min Range: -6.5343
Max Act: 6.2218. Min Act: -0.1700
Data Index: 3371821 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5343. Min Range: -6.5343
Max Act: 6.1281. Min Act: -0.1700
Data Index: 2889572 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5343. Min Range: -6.5343
Max Act: 6.1906. Min Act: -0.1700
Data Index: 1160241 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5343. Min Range: -6.5343
Max Act: 6.0968. Min Act: -0.1700
Data Index: 3542382 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5343. Min Range: -6.5343
Max Act: 6.1593. Min Act: -0.1700
Data Index: 6628790 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5343. Min Range: -6.5343
Max Act: 6.1281. Min Act: -0.1700
Data Index: 2511764 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5343. Min Range: -6.5343
Max Act: 6.1281. Min Act: -0.1700
Data Index: 4181203 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5343. Min Range: -6.5343
Max Act: 6.0968. Min Act: -0.1700
Data Index: 2442413 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5343. Min Range: -6.5343
Max Act: 6.0968. Min Act: -0.1700
Data Index: 5387320 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5343. Min Range: -6.5343
Max Act: 6.0968. Min Act: -0.1700
Data Index: 8067820 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5343. Min Range: -6.5343
Max Act: 6.0656. Min Act: -0.1700
Data Index: 3573676 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5343. Min Range: -6.5343
Max Act: 6.0968. Min Act: -0.1700
Data Index: 5185541 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5343. Min Range: -6.5343
Max Act: 6.0343. Min Act: -0.1700
Data Index: 608221 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5343. Min Range: -6.5343
Max Act: 6.0343. Min Act: -0.1700
Data Index: 5761285 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5343. Min Range: -6.5343
Max Act: 6.0656. Min Act: -0.1700
Data Index: 952395 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5343. Min Range: -6.5343
Max Act: 6.0656. Min Act: -0.1700
Data Index: 3405037 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #19