Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1859 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.1160. Min Range: -2.1160
Max Act: 2.1160. Min Act: -0.1700
Data Index: 3953393 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1160. Min Range: -2.1160
Max Act: 2.0993. Min Act: -0.1700
Data Index: 8096295 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1160. Min Range: -2.1160
Max Act: 2.0657. Min Act: -0.1700
Data Index: 560424 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1160. Min Range: -2.1160
Max Act: 2.0657. Min Act: -0.1700
Data Index: 1335204 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1160. Min Range: -2.1160
Max Act: 2.0321. Min Act: -0.1700
Data Index: 6015361 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1160. Min Range: -2.1160
Max Act: 2.0489. Min Act: -0.1700
Data Index: 2263519 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1160. Min Range: -2.1160
Max Act: 2.0152. Min Act: -0.1700
Data Index: 4894036 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1160. Min Range: -2.1160
Max Act: 2.0489. Min Act: -0.1699
Data Index: 4293158 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1160. Min Range: -2.1160
Max Act: 2.0489. Min Act: -0.1696
Data Index: 1495191 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1160. Min Range: -2.1160
Max Act: 2.0152. Min Act: -0.1700
Data Index: 1044764 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1160. Min Range: -2.1160
Max Act: 2.0152. Min Act: -0.1700
Data Index: 8551343 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1160. Min Range: -2.1160
Max Act: 2.0152. Min Act: -0.1700
Data Index: 8214102 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1160. Min Range: -2.1160
Max Act: 2.0152. Min Act: -0.1700
Data Index: 477416 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1160. Min Range: -2.1160
Max Act: 1.9983. Min Act: -0.1700
Data Index: 1459702 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1160. Min Range: -2.1160
Max Act: 1.9983. Min Act: -0.1699
Data Index: 4667653 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1160. Min Range: -2.1160
Max Act: 2.0152. Min Act: -0.1700
Data Index: 4400720 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1160. Min Range: -2.1160
Max Act: 2.0152. Min Act: -0.1700
Data Index: 5885398 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1160. Min Range: -2.1160
Max Act: 2.0152. Min Act: -0.1700
Data Index: 2264948 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1160. Min Range: -2.1160
Max Act: 1.9814. Min Act: -0.1700
Data Index: 796560 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1160. Min Range: -2.1160
Max Act: 1.9983. Min Act: -0.1700
Data Index: 4850393 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #19