Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1934 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7896. Min Range: -5.7896
Max Act: 5.7896. Min Act: -0.1700
Data Index: 2132625 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7896. Min Range: -5.7896
Max Act: 5.6958. Min Act: -0.1700
Data Index: 8594778 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7896. Min Range: -5.7896
Max Act: 5.5708. Min Act: -0.1700
Data Index: 1724163 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7896. Min Range: -5.7896
Max Act: 5.5708. Min Act: -0.1700
Data Index: 513273 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7896. Min Range: -5.7896
Max Act: 5.5083. Min Act: -0.1700
Data Index: 4842991 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7896. Min Range: -5.7896
Max Act: 5.5083. Min Act: -0.1700
Data Index: 5911831 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7896. Min Range: -5.7896
Max Act: 5.5396. Min Act: -0.1700
Data Index: 3189115 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7896. Min Range: -5.7896
Max Act: 5.4771. Min Act: -0.1700
Data Index: 7006072 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7896. Min Range: -5.7896
Max Act: 5.5083. Min Act: -0.1700
Data Index: 2023384 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7896. Min Range: -5.7896
Max Act: 5.4771. Min Act: -0.1700
Data Index: 4720421 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7896. Min Range: -5.7896
Max Act: 5.4458. Min Act: -0.1700
Data Index: 8343616 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7896. Min Range: -5.7896
Max Act: 5.4458. Min Act: -0.1700
Data Index: 2290009 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7896. Min Range: -5.7896
Max Act: 5.4146. Min Act: -0.1700
Data Index: 4616959 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7896. Min Range: -5.7896
Max Act: 5.4146. Min Act: -0.1700
Data Index: 1840316 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7896. Min Range: -5.7896
Max Act: 5.3833. Min Act: -0.1700
Data Index: 660406 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7896. Min Range: -5.7896
Max Act: 5.3208. Min Act: -0.1700
Data Index: 2926934 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7896. Min Range: -5.7896
Max Act: 5.2896. Min Act: -0.1700
Data Index: 7082371 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7896. Min Range: -5.7896
Max Act: 5.3208. Min Act: -0.1700
Data Index: 6273509 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7896. Min Range: -5.7896
Max Act: 5.3208. Min Act: -0.1700
Data Index: 7266401 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7896. Min Range: -5.7896
Max Act: 5.2896. Min Act: -0.1700
Data Index: 8148960 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #19