Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2987 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.2224. Min Range: -10.2224
Max Act: 10.2224. Min Act: -0.1700
Data Index: 6246207 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.2224. Min Range: -10.2224
Max Act: 9.7849. Min Act: -0.1700
Data Index: 7840740 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.2224. Min Range: -10.2224
Max Act: 9.7849. Min Act: -0.1700
Data Index: 454272 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.2224. Min Range: -10.2224
Max Act: 9.7224. Min Act: -0.1700
Data Index: 2730496 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.2224. Min Range: -10.2224
Max Act: 9.7224. Min Act: -0.1700
Data Index: 5982858 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.2224. Min Range: -10.2224
Max Act: 9.5974. Min Act: -0.1700
Data Index: 7456205 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.2224. Min Range: -10.2224
Max Act: 9.5974. Min Act: -0.1700
Data Index: 5138851 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.2224. Min Range: -10.2224
Max Act: 9.5349. Min Act: -0.1700
Data Index: 3988464 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.2224. Min Range: -10.2224
Max Act: 9.3474. Min Act: -0.1700
Data Index: 6204825 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.2224. Min Range: -10.2224
Max Act: 9.2849. Min Act: -0.1700
Data Index: 6612280 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.2224. Min Range: -10.2224
Max Act: 9.2224. Min Act: -0.1700
Data Index: 4727113 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.2224. Min Range: -10.2224
Max Act: 9.2224. Min Act: -0.1700
Data Index: 4590519 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.2224. Min Range: -10.2224
Max Act: 9.2224. Min Act: -0.1700
Data Index: 3156277 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.2224. Min Range: -10.2224
Max Act: 9.1599. Min Act: -0.1700
Data Index: 1330328 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.2224. Min Range: -10.2224
Max Act: 9.1599. Min Act: -0.1700
Data Index: 6752428 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.2224. Min Range: -10.2224
Max Act: 9.0974. Min Act: -0.1700
Data Index: 3149787 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.2224. Min Range: -10.2224
Max Act: 9.0974. Min Act: -0.1700
Data Index: 4591134 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.2224. Min Range: -10.2224
Max Act: 9.0974. Min Act: -0.1700
Data Index: 3278082 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.2224. Min Range: -10.2224
Max Act: 9.0974. Min Act: -0.1700
Data Index: 1483598 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.2224. Min Range: -10.2224
Max Act: 9.0349. Min Act: -0.1700
Data Index: 836667 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #19