Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5995 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9621. Min Range: -3.9621
Max Act: 3.9621. Min Act: -0.1700
Data Index: 7217107 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9621. Min Range: -3.9621
Max Act: 3.8996. Min Act: -0.1700
Data Index: 3514383 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9621. Min Range: -3.9621
Max Act: 3.8996. Min Act: -0.1700
Data Index: 6874461 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9621. Min Range: -3.9621
Max Act: 3.8683. Min Act: -0.1700
Data Index: 420928 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9621. Min Range: -3.9621
Max Act: 3.8683. Min Act: -0.1700
Data Index: 5370554 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9621. Min Range: -3.9621
Max Act: 3.8683. Min Act: -0.1700
Data Index: 1793187 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9621. Min Range: -3.9621
Max Act: 3.8683. Min Act: -0.1700
Data Index: 5222170 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9621. Min Range: -3.9621
Max Act: 3.8371. Min Act: -0.1700
Data Index: 795511 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9621. Min Range: -3.9621
Max Act: 3.8371. Min Act: -0.1700
Data Index: 2216420 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9621. Min Range: -3.9621
Max Act: 3.8058. Min Act: -0.1700
Data Index: 8641678 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9621. Min Range: -3.9621
Max Act: 3.8058. Min Act: -0.1700
Data Index: 5075206 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9621. Min Range: -3.9621
Max Act: 3.8058. Min Act: -0.1700
Data Index: 5360908 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9621. Min Range: -3.9621
Max Act: 3.8058. Min Act: -0.1699
Data Index: 3694568 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9621. Min Range: -3.9621
Max Act: 3.8058. Min Act: -0.1700
Data Index: 930522 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9621. Min Range: -3.9621
Max Act: 3.8058. Min Act: -0.1700
Data Index: 5697293 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9621. Min Range: -3.9621
Max Act: 3.7745. Min Act: -0.1700
Data Index: 3757 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9621. Min Range: -3.9621
Max Act: 3.7745. Min Act: -0.1700
Data Index: 1474265 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9621. Min Range: -3.9621
Max Act: 3.7432. Min Act: -0.1700
Data Index: 476765 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9621. Min Range: -3.9621
Max Act: 3.7745. Min Act: -0.1700
Data Index: 5505210 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9621. Min Range: -3.9621
Max Act: 3.7745. Min Act: -0.1700
Data Index: 6159773 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19