Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2722 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1958. Min Range: -7.1958
Max Act: 7.1958. Min Act: -0.1700
Data Index: 4006848 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1958. Min Range: -7.1958
Max Act: 6.8833. Min Act: -0.1700
Data Index: 3328725 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1958. Min Range: -7.1958
Max Act: 6.7271. Min Act: -0.1700
Data Index: 1306979 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1958. Min Range: -7.1958
Max Act: 6.6958. Min Act: -0.1700
Data Index: 3988961 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1958. Min Range: -7.1958
Max Act: 6.6646. Min Act: -0.1700
Data Index: 3975852 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1958. Min Range: -7.1958
Max Act: 6.6646. Min Act: -0.1700
Data Index: 3200636 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1958. Min Range: -7.1958
Max Act: 6.6021. Min Act: -0.1700
Data Index: 523818 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1958. Min Range: -7.1958
Max Act: 6.6021. Min Act: -0.1700
Data Index: 8025081 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1958. Min Range: -7.1958
Max Act: 6.5083. Min Act: -0.1700
Data Index: 1645117 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1958. Min Range: -7.1958
Max Act: 6.4771. Min Act: -0.1700
Data Index: 3737945 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1958. Min Range: -7.1958
Max Act: 6.4458. Min Act: -0.1700
Data Index: 6421199 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1958. Min Range: -7.1958
Max Act: 6.4458. Min Act: -0.1700
Data Index: 3516582 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1958. Min Range: -7.1958
Max Act: 6.4458. Min Act: -0.1700
Data Index: 8233354 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1958. Min Range: -7.1958
Max Act: 6.4146. Min Act: -0.1700
Data Index: 5891528 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1958. Min Range: -7.1958
Max Act: 6.4146. Min Act: -0.1700
Data Index: 3328724 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1958. Min Range: -7.1958
Max Act: 6.4146. Min Act: -0.1700
Data Index: 3199217 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1958. Min Range: -7.1958
Max Act: 6.4146. Min Act: -0.1700
Data Index: 1161592 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1958. Min Range: -7.1958
Max Act: 6.3521. Min Act: -0.1700
Data Index: 8048472 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1958. Min Range: -7.1958
Max Act: 6.3833. Min Act: -0.1700
Data Index: 7964769 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1958. Min Range: -7.1958
Max Act: 6.3521. Min Act: -0.1700
Data Index: 549657 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #19