Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3977 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9731. Min Range: -4.9731
Max Act: 4.9731. Min Act: -0.1700
Data Index: 5549062 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9731. Min Range: -4.9731
Max Act: 4.8793. Min Act: -0.1700
Data Index: 1996838 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9731. Min Range: -4.9731
Max Act: 4.8793. Min Act: -0.1700
Data Index: 6598578 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9731. Min Range: -4.9731
Max Act: 4.8168. Min Act: -0.1700
Data Index: 1939773 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9731. Min Range: -4.9731
Max Act: 4.8481. Min Act: -0.1700
Data Index: 2325091 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9731. Min Range: -4.9731
Max Act: 4.7856. Min Act: -0.1700
Data Index: 922513 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9731. Min Range: -4.9731
Max Act: 4.7856. Min Act: -0.1700
Data Index: 5452167 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9731. Min Range: -4.9731
Max Act: 4.7856. Min Act: -0.1700
Data Index: 7455428 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9731. Min Range: -4.9731
Max Act: 4.7231. Min Act: -0.1700
Data Index: 2010891 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9731. Min Range: -4.9731
Max Act: 4.6918. Min Act: -0.1700
Data Index: 7848835 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9731. Min Range: -4.9731
Max Act: 4.6606. Min Act: -0.1700
Data Index: 2395064 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9731. Min Range: -4.9731
Max Act: 4.6606. Min Act: -0.1700
Data Index: 5491882 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9731. Min Range: -4.9731
Max Act: 4.5981. Min Act: -0.1700
Data Index: 3826071 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9731. Min Range: -4.9731
Max Act: 4.6293. Min Act: -0.1700
Data Index: 2342512 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9731. Min Range: -4.9731
Max Act: 4.5668. Min Act: -0.1700
Data Index: 8494057 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9731. Min Range: -4.9731
Max Act: 4.5043. Min Act: -0.1700
Data Index: 6654150 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9731. Min Range: -4.9731
Max Act: 4.5043. Min Act: -0.1700
Data Index: 7647265 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9731. Min Range: -4.9731
Max Act: 4.5356. Min Act: -0.1700
Data Index: 5098303 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9731. Min Range: -4.9731
Max Act: 4.5043. Min Act: -0.1700
Data Index: 6361613 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9731. Min Range: -4.9731
Max Act: 4.5043. Min Act: -0.1700
Data Index: 3537937 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #19