Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2800 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2138. Min Range: -4.2138
Max Act: 4.2138. Min Act: -0.1700
Data Index: 6349357 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2138. Min Range: -4.2138
Max Act: 3.8699. Min Act: -0.1700
Data Index: 3964097 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2138. Min Range: -4.2138
Max Act: 3.8386. Min Act: -0.1700
Data Index: 1786584 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2138. Min Range: -4.2138
Max Act: 3.8386. Min Act: -0.1700
Data Index: 820207 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2138. Min Range: -4.2138
Max Act: 3.7917. Min Act: -0.1700
Data Index: 4324704 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2138. Min Range: -4.2138
Max Act: 3.7761. Min Act: -0.1700
Data Index: 6447538 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2138. Min Range: -4.2138
Max Act: 3.7761. Min Act: -0.1700
Data Index: 3333933 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2138. Min Range: -4.2138
Max Act: 3.7605. Min Act: -0.1700
Data Index: 5996447 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2138. Min Range: -4.2138
Max Act: 3.7135. Min Act: -0.1700
Data Index: 5467037 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2138. Min Range: -4.2138
Max Act: 3.6666. Min Act: -0.1700
Data Index: 3947032 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2138. Min Range: -4.2138
Max Act: 3.6979. Min Act: -0.1700
Data Index: 3693837 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2138. Min Range: -4.2138
Max Act: 3.6666. Min Act: -0.1700
Data Index: 4778917 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2138. Min Range: -4.2138
Max Act: 3.6353. Min Act: -0.1700
Data Index: 6892136 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2138. Min Range: -4.2138
Max Act: 3.6510. Min Act: -0.1700
Data Index: 626311 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2138. Min Range: -4.2138
Max Act: 3.6510. Min Act: -0.1700
Data Index: 8623499 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2138. Min Range: -4.2138
Max Act: 3.6197. Min Act: -0.1700
Data Index: 923895 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2138. Min Range: -4.2138
Max Act: 3.6040. Min Act: -0.1700
Data Index: 2430513 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2138. Min Range: -4.2138
Max Act: 3.6197. Min Act: -0.1700
Data Index: 5099683 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2138. Min Range: -4.2138
Max Act: 3.6040. Min Act: -0.1700
Data Index: 3734477 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2138. Min Range: -4.2138
Max Act: 3.6197. Min Act: -0.1700
Data Index: 2507607 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #19