Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2689 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.1282. Min Range: -7.1282
Max Act: 7.1282. Min Act: -0.1700
Data Index: 1393729 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1282. Min Range: -7.1282
Max Act: 7.0344. Min Act: -0.1700
Data Index: 1948985 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1282. Min Range: -7.1282
Max Act: 6.9407. Min Act: -0.1700
Data Index: 2078 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1282. Min Range: -7.1282
Max Act: 6.8157. Min Act: -0.1700
Data Index: 1290331 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1282. Min Range: -7.1282
Max Act: 6.7844. Min Act: -0.1700
Data Index: 8464093 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1282. Min Range: -7.1282
Max Act: 6.8157. Min Act: -0.1700
Data Index: 3149383 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1282. Min Range: -7.1282
Max Act: 6.7532. Min Act: -0.1700
Data Index: 6579672 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1282. Min Range: -7.1282
Max Act: 6.7532. Min Act: -0.1700
Data Index: 3253576 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1282. Min Range: -7.1282
Max Act: 6.7844. Min Act: -0.1700
Data Index: 5016853 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1282. Min Range: -7.1282
Max Act: 6.7844. Min Act: -0.1700
Data Index: 4912840 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1282. Min Range: -7.1282
Max Act: 6.7532. Min Act: -0.1700
Data Index: 646322 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1282. Min Range: -7.1282
Max Act: 6.6907. Min Act: -0.1700
Data Index: 4577203 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1282. Min Range: -7.1282
Max Act: 6.6594. Min Act: -0.1700
Data Index: 8261459 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1282. Min Range: -7.1282
Max Act: 6.6594. Min Act: -0.1700
Data Index: 2010639 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1282. Min Range: -7.1282
Max Act: 6.6594. Min Act: -0.1700
Data Index: 1232242 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1282. Min Range: -7.1282
Max Act: 6.6282. Min Act: -0.1700
Data Index: 3720972 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1282. Min Range: -7.1282
Max Act: 6.5969. Min Act: -0.1700
Data Index: 4192486 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1282. Min Range: -7.1282
Max Act: 6.5969. Min Act: -0.1700
Data Index: 3092805 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1282. Min Range: -7.1282
Max Act: 6.5657. Min Act: -0.1700
Data Index: 4147271 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1282. Min Range: -7.1282
Max Act: 6.6282. Min Act: -0.1700
Data Index: 5904441 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #19