Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2324 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7960. Min Range: -6.7960
Max Act: 6.7960. Min Act: -0.1700
Data Index: 933170 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7960. Min Range: -6.7960
Max Act: 6.7960. Min Act: -0.1700
Data Index: 6866670 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7960. Min Range: -6.7960
Max Act: 6.7647. Min Act: -0.1700
Data Index: 8223481 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7960. Min Range: -6.7960
Max Act: 6.7647. Min Act: -0.1700
Data Index: 8094055 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7960. Min Range: -6.7960
Max Act: 6.7647. Min Act: -0.1700
Data Index: 1220411 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7960. Min Range: -6.7960
Max Act: 6.6710. Min Act: -0.1700
Data Index: 5747697 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7960. Min Range: -6.7960
Max Act: 6.7022. Min Act: -0.1700
Data Index: 6194128 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7960. Min Range: -6.7960
Max Act: 6.7022. Min Act: -0.1700
Data Index: 6787909 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7960. Min Range: -6.7960
Max Act: 6.6710. Min Act: -0.1700
Data Index: 6557396 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7960. Min Range: -6.7960
Max Act: 6.6710. Min Act: -0.1700
Data Index: 5617674 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7960. Min Range: -6.7960
Max Act: 6.6397. Min Act: -0.1700
Data Index: 2784013 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7960. Min Range: -6.7960
Max Act: 6.6085. Min Act: -0.1700
Data Index: 2081944 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7960. Min Range: -6.7960
Max Act: 6.6397. Min Act: -0.1700
Data Index: 7604519 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7960. Min Range: -6.7960
Max Act: 6.6397. Min Act: -0.1700
Data Index: 5577483 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7960. Min Range: -6.7960
Max Act: 6.6397. Min Act: -0.1700
Data Index: 6232799 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7960. Min Range: -6.7960
Max Act: 6.6085. Min Act: -0.1700
Data Index: 2971438 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7960. Min Range: -6.7960
Max Act: 6.6085. Min Act: -0.1700
Data Index: 2891202 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7960. Min Range: -6.7960
Max Act: 6.6085. Min Act: -0.1700
Data Index: 467901 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7960. Min Range: -6.7960
Max Act: 6.6397. Min Act: -0.1700
Data Index: 5864910 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7960. Min Range: -6.7960
Max Act: 6.5460. Min Act: -0.1700
Data Index: 6004860 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #19