Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2819 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.4044. Min Range: -0.4044
Max Act: 0.4044. Min Act: -0.1676
Data Index: 223462 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.4044. Min Range: -0.4044
Max Act: 0.4044. Min Act: -0.1697
Data Index: 1991028 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.4044. Min Range: -0.4044
Max Act: 0.3694. Min Act: -0.1607
Data Index: 3278691 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.4044. Min Range: -0.4044
Max Act: 0.3557. Min Act: -0.1544
Data Index: 2740808 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.4044. Min Range: -0.4044
Max Act: 0.3353. Min Act: -0.1657
Data Index: 894620 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.4044. Min Range: -0.4044
Max Act: 0.3286. Min Act: -0.1680
Data Index: 6666436 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.4044. Min Range: -0.4044
Max Act: 0.3154. Min Act: -0.1450
Data Index: 8270688 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.4044. Min Range: -0.4044
Max Act: 0.3022. Min Act: -0.1648
Data Index: 7882684 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.4044. Min Range: -0.4044
Max Act: 0.3154. Min Act: -0.1692
Data Index: 2529163 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.4044. Min Range: -0.4044
Max Act: 0.3088. Min Act: -0.1700
Data Index: 3286262 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.4044. Min Range: -0.4044
Max Act: 0.3088. Min Act: -0.1658
Data Index: 8135052 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.4044. Min Range: -0.4044
Max Act: 0.3022. Min Act: -0.1638
Data Index: 4873248 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.4044. Min Range: -0.4044
Max Act: 0.3022. Min Act: -0.1697
Data Index: 8780615 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.4044. Min Range: -0.4044
Max Act: 0.2957. Min Act: -0.1426
Data Index: 6257638 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.4044. Min Range: -0.4044
Max Act: 0.2828. Min Act: -0.1644
Data Index: 4661429 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.4044. Min Range: -0.4044
Max Act: 0.2701. Min Act: -0.1699
Data Index: 1596658 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.4044. Min Range: -0.4044
Max Act: 0.2701. Min Act: -0.1700
Data Index: 6145447 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.4044. Min Range: -0.4044
Max Act: 0.2452. Min Act: -0.1568
Data Index: 1147800 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.4044. Min Range: -0.4044
Max Act: 0.2452. Min Act: -0.1676
Data Index: 5102077 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.4044. Min Range: -0.4044
Max Act: 0.2390. Min Act: -0.1278
Data Index: 67025 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #19