Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3445 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1344. Min Range: -4.1344
Max Act: 4.1344. Min Act: -0.1700
Data Index: 3789633 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1344. Min Range: -4.1344
Max Act: 4.0719. Min Act: -0.1700
Data Index: 3418237 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1344. Min Range: -4.1344
Max Act: 4.0407. Min Act: -0.1700
Data Index: 3215616 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1344. Min Range: -4.1344
Max Act: 4.0407. Min Act: -0.1700
Data Index: 3567181 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1344. Min Range: -4.1344
Max Act: 4.0094. Min Act: -0.1700
Data Index: 6979176 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1344. Min Range: -4.1344
Max Act: 3.9782. Min Act: -0.1700
Data Index: 8337069 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1344. Min Range: -4.1344
Max Act: 3.9782. Min Act: -0.1700
Data Index: 4850325 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1344. Min Range: -4.1344
Max Act: 3.9782. Min Act: -0.1700
Data Index: 2811308 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1344. Min Range: -4.1344
Max Act: 3.9782. Min Act: -0.1700
Data Index: 2818016 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1344. Min Range: -4.1344
Max Act: 3.9782. Min Act: -0.1700
Data Index: 6228839 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1344. Min Range: -4.1344
Max Act: 3.9782. Min Act: -0.1700
Data Index: 696935 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1344. Min Range: -4.1344
Max Act: 3.9782. Min Act: -0.1700
Data Index: 1112748 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1344. Min Range: -4.1344
Max Act: 3.9782. Min Act: -0.1700
Data Index: 2129613 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1344. Min Range: -4.1344
Max Act: 3.9469. Min Act: -0.1700
Data Index: 7170069 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1344. Min Range: -4.1344
Max Act: 3.9782. Min Act: -0.1700
Data Index: 4710631 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1344. Min Range: -4.1344
Max Act: 3.9469. Min Act: -0.1700
Data Index: 2052165 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1344. Min Range: -4.1344
Max Act: 3.9469. Min Act: -0.1700
Data Index: 3091650 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1344. Min Range: -4.1344
Max Act: 3.9469. Min Act: -0.1700
Data Index: 3523190 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1344. Min Range: -4.1344
Max Act: 3.9156. Min Act: -0.1700
Data Index: 609572 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1344. Min Range: -4.1344
Max Act: 3.9156. Min Act: -0.1700
Data Index: 5976791 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19