Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5592 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7650. Min Range: -4.7650
Max Act: 4.7650. Min Act: -0.1700
Data Index: 6069089 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7650. Min Range: -4.7650
Max Act: 4.6713. Min Act: -0.1700
Data Index: 5861324 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7650. Min Range: -4.7650
Max Act: 4.5463. Min Act: -0.1700
Data Index: 6979772 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7650. Min Range: -4.7650
Max Act: 4.5463. Min Act: -0.1700
Data Index: 7261225 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7650. Min Range: -4.7650
Max Act: 4.4525. Min Act: -0.1700
Data Index: 7346969 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7650. Min Range: -4.7650
Max Act: 4.4838. Min Act: -0.1700
Data Index: 683240 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7650. Min Range: -4.7650
Max Act: 4.4525. Min Act: -0.1700
Data Index: 2064435 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7650. Min Range: -4.7650
Max Act: 4.4213. Min Act: -0.1700
Data Index: 976609 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7650. Min Range: -4.7650
Max Act: 4.4213. Min Act: -0.1700
Data Index: 3070522 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7650. Min Range: -4.7650
Max Act: 4.4213. Min Act: -0.1700
Data Index: 2146646 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7650. Min Range: -4.7650
Max Act: 4.3900. Min Act: -0.1700
Data Index: 4669901 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7650. Min Range: -4.7650
Max Act: 4.4213. Min Act: -0.1700
Data Index: 1498026 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7650. Min Range: -4.7650
Max Act: 4.3900. Min Act: -0.1700
Data Index: 5988965 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7650. Min Range: -4.7650
Max Act: 4.3900. Min Act: -0.1700
Data Index: 8776134 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7650. Min Range: -4.7650
Max Act: 4.3900. Min Act: -0.1700
Data Index: 5677966 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7650. Min Range: -4.7650
Max Act: 4.3900. Min Act: -0.1700
Data Index: 8793909 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7650. Min Range: -4.7650
Max Act: 4.3587. Min Act: -0.1700
Data Index: 4594387 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7650. Min Range: -4.7650
Max Act: 4.3587. Min Act: -0.1700
Data Index: 1653883 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7650. Min Range: -4.7650
Max Act: 4.3587. Min Act: -0.1700
Data Index: 3927876 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7650. Min Range: -4.7650
Max Act: 4.3587. Min Act: -0.1700
Data Index: 5874516 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #19