Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3023 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9472. Min Range: -6.9472
Max Act: 6.9472. Min Act: -0.1700
Data Index: 1444086 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9472. Min Range: -6.9472
Max Act: 6.9472. Min Act: -0.1700
Data Index: 2861970 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9472. Min Range: -6.9472
Max Act: 6.9160. Min Act: -0.1700
Data Index: 6367476 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9472. Min Range: -6.9472
Max Act: 6.9160. Min Act: -0.1700
Data Index: 525072 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9472. Min Range: -6.9472
Max Act: 6.8535. Min Act: -0.1700
Data Index: 6834983 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9472. Min Range: -6.9472
Max Act: 6.6972. Min Act: -0.1700
Data Index: 643892 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9472. Min Range: -6.9472
Max Act: 6.5722. Min Act: -0.1700
Data Index: 4650693 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9472. Min Range: -6.9472
Max Act: 6.5410. Min Act: -0.1700
Data Index: 2790104 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9472. Min Range: -6.9472
Max Act: 6.5410. Min Act: -0.1700
Data Index: 5285892 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9472. Min Range: -6.9472
Max Act: 6.5722. Min Act: -0.1700
Data Index: 4041339 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9472. Min Range: -6.9472
Max Act: 6.5097. Min Act: -0.1700
Data Index: 5062307 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9472. Min Range: -6.9472
Max Act: 6.4785. Min Act: -0.1700
Data Index: 4472213 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9472. Min Range: -6.9472
Max Act: 6.5097. Min Act: -0.1700
Data Index: 6689562 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9472. Min Range: -6.9472
Max Act: 6.4472. Min Act: -0.1700
Data Index: 5577566 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9472. Min Range: -6.9472
Max Act: 6.4472. Min Act: -0.1700
Data Index: 6053737 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9472. Min Range: -6.9472
Max Act: 6.4472. Min Act: -0.1700
Data Index: 5472223 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9472. Min Range: -6.9472
Max Act: 6.4472. Min Act: -0.1700
Data Index: 6355384 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9472. Min Range: -6.9472
Max Act: 6.4160. Min Act: -0.1700
Data Index: 2091288 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9472. Min Range: -6.9472
Max Act: 6.4160. Min Act: -0.1700
Data Index: 608633 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9472. Min Range: -6.9472
Max Act: 6.4472. Min Act: -0.1700
Data Index: 8100416 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #19