Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3805 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5623. Min Range: -4.5623
Max Act: 4.5623. Min Act: -0.1700
Data Index: 3222167 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5623. Min Range: -4.5623
Max Act: 4.3435. Min Act: -0.1700
Data Index: 7738764 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5623. Min Range: -4.5623
Max Act: 4.2810. Min Act: -0.1700
Data Index: 7408783 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5623. Min Range: -4.5623
Max Act: 4.2810. Min Act: -0.1700
Data Index: 2610693 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5623. Min Range: -4.5623
Max Act: 4.1247. Min Act: -0.1700
Data Index: 4740832 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5623. Min Range: -4.5623
Max Act: 4.0935. Min Act: -0.1700
Data Index: 7742946 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5623. Min Range: -4.5623
Max Act: 4.0622. Min Act: -0.1700
Data Index: 2022178 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5623. Min Range: -4.5623
Max Act: 4.0310. Min Act: -0.1700
Data Index: 2684484 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5623. Min Range: -4.5623
Max Act: 4.0310. Min Act: -0.1700
Data Index: 6024455 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5623. Min Range: -4.5623
Max Act: 4.0310. Min Act: -0.1700
Data Index: 2919040 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5623. Min Range: -4.5623
Max Act: 4.0310. Min Act: -0.1700
Data Index: 81013 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5623. Min Range: -4.5623
Max Act: 3.9997. Min Act: -0.1700
Data Index: 7908795 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5623. Min Range: -4.5623
Max Act: 3.9684. Min Act: -0.1700
Data Index: 2056998 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5623. Min Range: -4.5623
Max Act: 3.9997. Min Act: -0.1700
Data Index: 7450501 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5623. Min Range: -4.5623
Max Act: 3.9997. Min Act: -0.1700
Data Index: 8726097 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5623. Min Range: -4.5623
Max Act: 3.9684. Min Act: -0.1700
Data Index: 5689273 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5623. Min Range: -4.5623
Max Act: 3.9684. Min Act: -0.1700
Data Index: 2861839 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5623. Min Range: -4.5623
Max Act: 3.9684. Min Act: -0.1700
Data Index: 6046760 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5623. Min Range: -4.5623
Max Act: 3.9684. Min Act: -0.1700
Data Index: 7208086 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5623. Min Range: -4.5623
Max Act: 3.9684. Min Act: -0.1700
Data Index: 2577318 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #19