Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2415 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3431. Min Range: -3.3431
Max Act: 3.3431. Min Act: -0.1700
Data Index: 8642300 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3431. Min Range: -3.3431
Max Act: 3.3274. Min Act: -0.1700
Data Index: 1051324 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3431. Min Range: -3.3431
Max Act: 3.2960. Min Act: -0.1700
Data Index: 7913781 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3431. Min Range: -3.3431
Max Act: 3.2803. Min Act: -0.1700
Data Index: 1359141 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3431. Min Range: -3.3431
Max Act: 3.2332. Min Act: -0.1700
Data Index: 7583690 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3431. Min Range: -3.3431
Max Act: 3.2017. Min Act: -0.1700
Data Index: 6431849 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3431. Min Range: -3.3431
Max Act: 3.1860. Min Act: -0.1700
Data Index: 7827795 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3431. Min Range: -3.3431
Max Act: 3.1860. Min Act: -0.1700
Data Index: 5240194 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3431. Min Range: -3.3431
Max Act: 3.1703. Min Act: -0.1700
Data Index: 5018080 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3431. Min Range: -3.3431
Max Act: 3.2017. Min Act: -0.1700
Data Index: 4522023 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3431. Min Range: -3.3431
Max Act: 3.1703. Min Act: -0.1700
Data Index: 7869184 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3431. Min Range: -3.3431
Max Act: 3.1545. Min Act: -0.1700
Data Index: 3552906 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3431. Min Range: -3.3431
Max Act: 3.1703. Min Act: -0.1700
Data Index: 4883338 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3431. Min Range: -3.3431
Max Act: 3.1703. Min Act: -0.1700
Data Index: 1155988 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3431. Min Range: -3.3431
Max Act: 3.1703. Min Act: -0.1700
Data Index: 4398074 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3431. Min Range: -3.3431
Max Act: 3.1703. Min Act: -0.1700
Data Index: 4320874 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3431. Min Range: -3.3431
Max Act: 3.1388. Min Act: -0.1700
Data Index: 6399814 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3431. Min Range: -3.3431
Max Act: 3.1388. Min Act: -0.1700
Data Index: 3262798 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3431. Min Range: -3.3431
Max Act: 3.1230. Min Act: -0.1700
Data Index: 3061359 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3431. Min Range: -3.3431
Max Act: 3.1388. Min Act: -0.1700
Data Index: 5979168 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #19