Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1961 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1152. Min Range: -3.1152
Max Act: 3.1152. Min Act: -0.1700
Data Index: 619315 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1152. Min Range: -3.1152
Max Act: 3.1152. Min Act: -0.1700
Data Index: 7900734 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1152. Min Range: -3.1152
Max Act: 3.0363. Min Act: -0.1700
Data Index: 8328062 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1152. Min Range: -3.1152
Max Act: 3.0205. Min Act: -0.1700
Data Index: 7181010 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1152. Min Range: -3.1152
Max Act: 3.0205. Min Act: -0.1700
Data Index: 4762357 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1152. Min Range: -3.1152
Max Act: 3.0205. Min Act: -0.1700
Data Index: 7837504 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1152. Min Range: -3.1152
Max Act: 2.9889. Min Act: -0.1700
Data Index: 5171629 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1152. Min Range: -3.1152
Max Act: 2.9731. Min Act: -0.1700
Data Index: 1349667 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1152. Min Range: -3.1152
Max Act: 2.9256. Min Act: -0.1700
Data Index: 1537089 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1152. Min Range: -3.1152
Max Act: 2.9415. Min Act: -0.1700
Data Index: 6345571 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1152. Min Range: -3.1152
Max Act: 2.9415. Min Act: -0.1700
Data Index: 6327937 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1152. Min Range: -3.1152
Max Act: 2.9256. Min Act: -0.1700
Data Index: 4503167 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1152. Min Range: -3.1152
Max Act: 2.8939. Min Act: -0.1700
Data Index: 2314022 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1152. Min Range: -3.1152
Max Act: 2.8939. Min Act: -0.1700
Data Index: 5109618 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1152. Min Range: -3.1152
Max Act: 2.9098. Min Act: -0.1700
Data Index: 7970603 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1152. Min Range: -3.1152
Max Act: 2.8939. Min Act: -0.1700
Data Index: 7468939 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1152. Min Range: -3.1152
Max Act: 2.9098. Min Act: -0.1700
Data Index: 3104497 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1152. Min Range: -3.1152
Max Act: 2.8939. Min Act: -0.1700
Data Index: 5171630 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1152. Min Range: -3.1152
Max Act: 2.9098. Min Act: -0.1700
Data Index: 1931616 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1152. Min Range: -3.1152
Max Act: 2.9256. Min Act: -0.1700
Data Index: 6006185 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #19