Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3472 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8360. Min Range: -6.8360
Max Act: 6.8360. Min Act: -0.1700
Data Index: 4393997 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8360. Min Range: -6.8360
Max Act: 6.7110. Min Act: -0.1700
Data Index: 2544161 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8360. Min Range: -6.8360
Max Act: 6.7422. Min Act: -0.1700
Data Index: 616141 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8360. Min Range: -6.8360
Max Act: 6.4922. Min Act: -0.1700
Data Index: 5739280 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8360. Min Range: -6.8360
Max Act: 6.3985. Min Act: -0.1700
Data Index: 2449596 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8360. Min Range: -6.8360
Max Act: 6.3985. Min Act: -0.1700
Data Index: 7162046 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8360. Min Range: -6.8360
Max Act: 6.3360. Min Act: -0.1700
Data Index: 6070376 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8360. Min Range: -6.8360
Max Act: 6.3047. Min Act: -0.1700
Data Index: 4244709 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8360. Min Range: -6.8360
Max Act: 6.2735. Min Act: -0.1700
Data Index: 2752057 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8360. Min Range: -6.8360
Max Act: 6.2422. Min Act: -0.1700
Data Index: 3125820 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8360. Min Range: -6.8360
Max Act: 6.2422. Min Act: -0.1700
Data Index: 6601238 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8360. Min Range: -6.8360
Max Act: 6.1485. Min Act: -0.1700
Data Index: 8545094 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8360. Min Range: -6.8360
Max Act: 6.1172. Min Act: -0.1700
Data Index: 3996305 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8360. Min Range: -6.8360
Max Act: 6.1172. Min Act: -0.1700
Data Index: 5684628 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8360. Min Range: -6.8360
Max Act: 6.1172. Min Act: -0.1700
Data Index: 7238462 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8360. Min Range: -6.8360
Max Act: 6.0860. Min Act: -0.1700
Data Index: 8044700 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8360. Min Range: -6.8360
Max Act: 6.1172. Min Act: -0.1700
Data Index: 8280546 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8360. Min Range: -6.8360
Max Act: 6.0235. Min Act: -0.1700
Data Index: 4178541 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8360. Min Range: -6.8360
Max Act: 6.0235. Min Act: -0.1700
Data Index: 7483394 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8360. Min Range: -6.8360
Max Act: 5.9922. Min Act: -0.1700
Data Index: 1091790 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #19