Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1929 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5700. Min Range: -4.5700
Max Act: 4.5700. Min Act: -0.1700
Data Index: 8362309 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5700. Min Range: -4.5700
Max Act: 4.5388. Min Act: -0.1700
Data Index: 1324921 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5700. Min Range: -4.5700
Max Act: 4.4450. Min Act: -0.1700
Data Index: 858554 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5700. Min Range: -4.5700
Max Act: 4.4763. Min Act: -0.1700
Data Index: 1113819 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5700. Min Range: -4.5700
Max Act: 4.3825. Min Act: -0.1700
Data Index: 7082469 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5700. Min Range: -4.5700
Max Act: 4.4137. Min Act: -0.1700
Data Index: 2607380 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5700. Min Range: -4.5700
Max Act: 4.3825. Min Act: -0.1700
Data Index: 8292791 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5700. Min Range: -4.5700
Max Act: 4.4137. Min Act: -0.1700
Data Index: 5028985 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5700. Min Range: -4.5700
Max Act: 4.3825. Min Act: -0.1700
Data Index: 6036081 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5700. Min Range: -4.5700
Max Act: 4.3512. Min Act: -0.1699
Data Index: 2767813 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5700. Min Range: -4.5700
Max Act: 4.3512. Min Act: -0.1700
Data Index: 4735134 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5700. Min Range: -4.5700
Max Act: 4.3512. Min Act: -0.1700
Data Index: 7406593 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5700. Min Range: -4.5700
Max Act: 4.3200. Min Act: -0.1700
Data Index: 7418414 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5700. Min Range: -4.5700
Max Act: 4.3512. Min Act: -0.1700
Data Index: 8070393 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5700. Min Range: -4.5700
Max Act: 4.2887. Min Act: -0.1700
Data Index: 4959980 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5700. Min Range: -4.5700
Max Act: 4.3512. Min Act: -0.1700
Data Index: 8299117 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5700. Min Range: -4.5700
Max Act: 4.3512. Min Act: -0.1700
Data Index: 204998 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5700. Min Range: -4.5700
Max Act: 4.2887. Min Act: -0.1700
Data Index: 1114593 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5700. Min Range: -4.5700
Max Act: 4.3200. Min Act: -0.1700
Data Index: 2481655 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5700. Min Range: -4.5700
Max Act: 4.2887. Min Act: -0.1700
Data Index: 3755225 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #19