Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 728 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.1235. Min Range: -7.1235
Max Act: 7.1235. Min Act: -0.1700
Data Index: 6928589 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1235. Min Range: -7.1235
Max Act: 7.1235. Min Act: -0.1700
Data Index: 8147376 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1235. Min Range: -7.1235
Max Act: 6.9672. Min Act: -0.1700
Data Index: 3216048 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1235. Min Range: -7.1235
Max Act: 6.7797. Min Act: -0.1700
Data Index: 8050887 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1235. Min Range: -7.1235
Max Act: 6.7797. Min Act: -0.1700
Data Index: 6440267 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1235. Min Range: -7.1235
Max Act: 6.7485. Min Act: -0.1700
Data Index: 1695571 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1235. Min Range: -7.1235
Max Act: 6.6860. Min Act: -0.1700
Data Index: 601184 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1235. Min Range: -7.1235
Max Act: 6.6547. Min Act: -0.1700
Data Index: 6468873 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1235. Min Range: -7.1235
Max Act: 6.6235. Min Act: -0.1700
Data Index: 6987662 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1235. Min Range: -7.1235
Max Act: 6.6235. Min Act: -0.1700
Data Index: 7594751 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1235. Min Range: -7.1235
Max Act: 6.6235. Min Act: -0.1700
Data Index: 4048964 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1235. Min Range: -7.1235
Max Act: 6.5610. Min Act: -0.1700
Data Index: 2517911 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1235. Min Range: -7.1235
Max Act: 6.5610. Min Act: -0.1700
Data Index: 3983076 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1235. Min Range: -7.1235
Max Act: 6.5297. Min Act: -0.1700
Data Index: 6431131 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1235. Min Range: -7.1235
Max Act: 6.5297. Min Act: -0.1700
Data Index: 8281010 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1235. Min Range: -7.1235
Max Act: 6.5610. Min Act: -0.1700
Data Index: 2537054 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1235. Min Range: -7.1235
Max Act: 6.5297. Min Act: -0.1700
Data Index: 6302075 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1235. Min Range: -7.1235
Max Act: 6.5297. Min Act: -0.1700
Data Index: 855898 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1235. Min Range: -7.1235
Max Act: 6.5297. Min Act: -0.1700
Data Index: 4636960 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1235. Min Range: -7.1235
Max Act: 6.4672. Min Act: -0.1700
Data Index: 264158 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #19