Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2934 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1232. Min Range: -7.1232
Max Act: 7.1232. Min Act: -0.1700
Data Index: 1645504 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1232. Min Range: -7.1232
Max Act: 6.9670. Min Act: -0.1700
Data Index: 343074 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1232. Min Range: -7.1232
Max Act: 6.8420. Min Act: -0.1700
Data Index: 7436290 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1232. Min Range: -7.1232
Max Act: 6.7170. Min Act: -0.1700
Data Index: 6970460 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1232. Min Range: -7.1232
Max Act: 6.6857. Min Act: -0.1700
Data Index: 4162313 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1232. Min Range: -7.1232
Max Act: 6.6545. Min Act: -0.1700
Data Index: 6214677 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1232. Min Range: -7.1232
Max Act: 6.6545. Min Act: -0.1700
Data Index: 1265010 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1232. Min Range: -7.1232
Max Act: 6.6232. Min Act: -0.1700
Data Index: 8805140 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1232. Min Range: -7.1232
Max Act: 6.5920. Min Act: -0.1700
Data Index: 934421 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1232. Min Range: -7.1232
Max Act: 6.6232. Min Act: -0.1700
Data Index: 4864039 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1232. Min Range: -7.1232
Max Act: 6.5607. Min Act: -0.1700
Data Index: 6869475 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1232. Min Range: -7.1232
Max Act: 6.5607. Min Act: -0.1700
Data Index: 5030117 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1232. Min Range: -7.1232
Max Act: 6.5607. Min Act: -0.1700
Data Index: 4866624 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1232. Min Range: -7.1232
Max Act: 6.5295. Min Act: -0.1700
Data Index: 7886921 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1232. Min Range: -7.1232
Max Act: 6.4982. Min Act: -0.1700
Data Index: 658222 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1232. Min Range: -7.1232
Max Act: 6.5295. Min Act: -0.1700
Data Index: 395965 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1232. Min Range: -7.1232
Max Act: 6.4982. Min Act: -0.1700
Data Index: 5907160 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1232. Min Range: -7.1232
Max Act: 6.4982. Min Act: -0.1700
Data Index: 2150299 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1232. Min Range: -7.1232
Max Act: 6.4670. Min Act: -0.1700
Data Index: 2058380 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1232. Min Range: -7.1232
Max Act: 6.4670. Min Act: -0.1700
Data Index: 8058718 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #19