Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4700 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.6939. Min Range: -7.6939
Max Act: 7.6939. Min Act: -0.1700
Data Index: 274031 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6939. Min Range: -7.6939
Max Act: 7.5376. Min Act: -0.1700
Data Index: 4725522 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6939. Min Range: -7.6939
Max Act: 7.2876. Min Act: -0.1700
Data Index: 2967669 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6939. Min Range: -7.6939
Max Act: 7.2876. Min Act: -0.1700
Data Index: 6006464 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6939. Min Range: -7.6939
Max Act: 7.2251. Min Act: -0.1700
Data Index: 1879384 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6939. Min Range: -7.6939
Max Act: 7.1001. Min Act: -0.1700
Data Index: 5928869 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6939. Min Range: -7.6939
Max Act: 7.1314. Min Act: -0.1700
Data Index: 3855955 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6939. Min Range: -7.6939
Max Act: 7.0689. Min Act: -0.1700
Data Index: 8584184 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6939. Min Range: -7.6939
Max Act: 7.0376. Min Act: -0.1700
Data Index: 6041143 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6939. Min Range: -7.6939
Max Act: 7.0376. Min Act: -0.1700
Data Index: 6072897 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6939. Min Range: -7.6939
Max Act: 7.0376. Min Act: -0.1700
Data Index: 2425322 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6939. Min Range: -7.6939
Max Act: 6.9751. Min Act: -0.1700
Data Index: 4806769 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6939. Min Range: -7.6939
Max Act: 6.9751. Min Act: -0.1700
Data Index: 1397431 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6939. Min Range: -7.6939
Max Act: 7.0064. Min Act: -0.1700
Data Index: 7359558 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6939. Min Range: -7.6939
Max Act: 6.9751. Min Act: -0.1700
Data Index: 3479283 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6939. Min Range: -7.6939
Max Act: 6.9751. Min Act: -0.1700
Data Index: 3436283 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6939. Min Range: -7.6939
Max Act: 6.9751. Min Act: -0.1700
Data Index: 626249 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6939. Min Range: -7.6939
Max Act: 6.9126. Min Act: -0.1700
Data Index: 7119040 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6939. Min Range: -7.6939
Max Act: 6.9439. Min Act: -0.1700
Data Index: 2580801 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6939. Min Range: -7.6939
Max Act: 6.8814. Min Act: -0.1700
Data Index: 5276333 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #19