Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 407 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3198. Min Range: -3.3198
Max Act: 3.3198. Min Act: -0.1700
Data Index: 2479029 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3198. Min Range: -3.3198
Max Act: 3.1941. Min Act: -0.1700
Data Index: 3376362 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3198. Min Range: -3.3198
Max Act: 3.1784. Min Act: -0.1700
Data Index: 1259487 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3198. Min Range: -3.3198
Max Act: 3.1312. Min Act: -0.1700
Data Index: 7588540 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3198. Min Range: -3.3198
Max Act: 3.1154. Min Act: -0.1700
Data Index: 5876007 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3198. Min Range: -3.3198
Max Act: 3.0997. Min Act: -0.1700
Data Index: 6968545 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3198. Min Range: -3.3198
Max Act: 3.0997. Min Act: -0.1700
Data Index: 44439 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3198. Min Range: -3.3198
Max Act: 3.0839. Min Act: -0.1700
Data Index: 1375572 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3198. Min Range: -3.3198
Max Act: 2.9734. Min Act: -0.1700
Data Index: 7141898 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3198. Min Range: -3.3198
Max Act: 2.9734. Min Act: -0.1700
Data Index: 296655 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3198. Min Range: -3.3198
Max Act: 2.9575. Min Act: -0.1700
Data Index: 2447611 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3198. Min Range: -3.3198
Max Act: 2.9417. Min Act: -0.1700
Data Index: 4002871 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3198. Min Range: -3.3198
Max Act: 2.9417. Min Act: -0.1700
Data Index: 1887827 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3198. Min Range: -3.3198
Max Act: 2.9100. Min Act: -0.1700
Data Index: 7527919 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3198. Min Range: -3.3198
Max Act: 2.9417. Min Act: -0.1700
Data Index: 1263105 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3198. Min Range: -3.3198
Max Act: 2.8942. Min Act: -0.1700
Data Index: 2319695 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3198. Min Range: -3.3198
Max Act: 2.9259. Min Act: -0.1700
Data Index: 5841951 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3198. Min Range: -3.3198
Max Act: 2.9100. Min Act: -0.1700
Data Index: 6241383 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3198. Min Range: -3.3198
Max Act: 2.8942. Min Act: -0.1700
Data Index: 2372435 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3198. Min Range: -3.3198
Max Act: 2.8942. Min Act: -0.1700
Data Index: 427506 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #19