Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3228 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6881. Min Range: -5.6881
Max Act: 5.6881. Min Act: -0.1700
Data Index: 8814083 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6881. Min Range: -5.6881
Max Act: 5.6569. Min Act: -0.1700
Data Index: 5148298 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6881. Min Range: -5.6881
Max Act: 5.6256. Min Act: -0.1700
Data Index: 5359513 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6881. Min Range: -5.6881
Max Act: 5.5944. Min Act: -0.1700
Data Index: 2154687 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6881. Min Range: -5.6881
Max Act: 5.5944. Min Act: -0.1700
Data Index: 3183044 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6881. Min Range: -5.6881
Max Act: 5.5944. Min Act: -0.1700
Data Index: 2193852 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6881. Min Range: -5.6881
Max Act: 5.5631. Min Act: -0.1700
Data Index: 5359515 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6881. Min Range: -5.6881
Max Act: 5.5631. Min Act: -0.1700
Data Index: 8291664 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6881. Min Range: -5.6881
Max Act: 5.5319. Min Act: -0.1700
Data Index: 4423556 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6881. Min Range: -5.6881
Max Act: 5.5006. Min Act: -0.1700
Data Index: 4760321 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6881. Min Range: -5.6881
Max Act: 5.5006. Min Act: -0.1700
Data Index: 185124 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6881. Min Range: -5.6881
Max Act: 5.5006. Min Act: -0.1700
Data Index: 3157366 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6881. Min Range: -5.6881
Max Act: 5.4381. Min Act: -0.1700
Data Index: 5555495 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6881. Min Range: -5.6881
Max Act: 5.4694. Min Act: -0.1700
Data Index: 71248 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6881. Min Range: -5.6881
Max Act: 5.4694. Min Act: -0.1700
Data Index: 3183043 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6881. Min Range: -5.6881
Max Act: 5.5006. Min Act: -0.1700
Data Index: 4517710 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6881. Min Range: -5.6881
Max Act: 5.4381. Min Act: -0.1700
Data Index: 4525398 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6881. Min Range: -5.6881
Max Act: 5.4381. Min Act: -0.1700
Data Index: 1653976 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6881. Min Range: -5.6881
Max Act: 5.4381. Min Act: -0.1700
Data Index: 5359516 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6881. Min Range: -5.6881
Max Act: 5.4069. Min Act: -0.1700
Data Index: 7743102 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #19