Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5394 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2622. Min Range: -5.2622
Max Act: 5.2622. Min Act: -0.1700
Data Index: 5271687 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2622. Min Range: -5.2622
Max Act: 5.2309. Min Act: -0.1700
Data Index: 279059 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2622. Min Range: -5.2622
Max Act: 5.2309. Min Act: -0.1700
Data Index: 5271675 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2622. Min Range: -5.2622
Max Act: 5.1684. Min Act: -0.1700
Data Index: 5271685 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2622. Min Range: -5.2622
Max Act: 5.0747. Min Act: -0.1700
Data Index: 5271674 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2622. Min Range: -5.2622
Max Act: 5.0434. Min Act: -0.1700
Data Index: 5271688 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2622. Min Range: -5.2622
Max Act: 5.0434. Min Act: -0.1700
Data Index: 7139040 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2622. Min Range: -5.2622
Max Act: 4.9809. Min Act: -0.1700
Data Index: 4806051 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2622. Min Range: -5.2622
Max Act: 4.9809. Min Act: -0.1700
Data Index: 153798 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2622. Min Range: -5.2622
Max Act: 4.9497. Min Act: -0.1700
Data Index: 4279724 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2622. Min Range: -5.2622
Max Act: 4.9497. Min Act: -0.1700
Data Index: 289310 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2622. Min Range: -5.2622
Max Act: 4.9497. Min Act: -0.1700
Data Index: 2067273 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2622. Min Range: -5.2622
Max Act: 4.9184. Min Act: -0.1700
Data Index: 960379 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2622. Min Range: -5.2622
Max Act: 4.8872. Min Act: -0.1700
Data Index: 5190777 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2622. Min Range: -5.2622
Max Act: 4.8872. Min Act: -0.1700
Data Index: 8662765 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2622. Min Range: -5.2622
Max Act: 4.8872. Min Act: -0.1700
Data Index: 8114887 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2622. Min Range: -5.2622
Max Act: 4.8872. Min Act: -0.1700
Data Index: 8662766 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2622. Min Range: -5.2622
Max Act: 4.8559. Min Act: -0.1700
Data Index: 1020169 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2622. Min Range: -5.2622
Max Act: 4.8559. Min Act: -0.1700
Data Index: 1381310 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2622. Min Range: -5.2622
Max Act: 4.8559. Min Act: -0.1700
Data Index: 2472621 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #19