Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4360 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9124. Min Range: -5.9124
Max Act: 5.9124. Min Act: -0.1700
Data Index: 904225 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9124. Min Range: -5.9124
Max Act: 5.9124. Min Act: -0.1700
Data Index: 7455027 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9124. Min Range: -5.9124
Max Act: 5.8499. Min Act: -0.1700
Data Index: 6002487 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9124. Min Range: -5.9124
Max Act: 5.7874. Min Act: -0.1700
Data Index: 5628966 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9124. Min Range: -5.9124
Max Act: 5.7249. Min Act: -0.1700
Data Index: 2392532 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9124. Min Range: -5.9124
Max Act: 5.6937. Min Act: -0.1700
Data Index: 2666249 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9124. Min Range: -5.9124
Max Act: 5.7249. Min Act: -0.1700
Data Index: 7591811 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9124. Min Range: -5.9124
Max Act: 5.5374. Min Act: -0.1700
Data Index: 5107090 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9124. Min Range: -5.9124
Max Act: 5.5374. Min Act: -0.1700
Data Index: 1688118 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9124. Min Range: -5.9124
Max Act: 5.4749. Min Act: -0.1700
Data Index: 618421 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9124. Min Range: -5.9124
Max Act: 5.4749. Min Act: -0.1700
Data Index: 1186024 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9124. Min Range: -5.9124
Max Act: 5.4749. Min Act: -0.1700
Data Index: 4335669 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9124. Min Range: -5.9124
Max Act: 5.4124. Min Act: -0.1700
Data Index: 8065482 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9124. Min Range: -5.9124
Max Act: 5.4437. Min Act: -0.1700
Data Index: 3592970 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9124. Min Range: -5.9124
Max Act: 5.4124. Min Act: -0.1700
Data Index: 783914 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9124. Min Range: -5.9124
Max Act: 5.4124. Min Act: -0.1700
Data Index: 3707534 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9124. Min Range: -5.9124
Max Act: 5.3187. Min Act: -0.1700
Data Index: 6674209 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9124. Min Range: -5.9124
Max Act: 5.3499. Min Act: -0.1700
Data Index: 8765562 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9124. Min Range: -5.9124
Max Act: 5.3499. Min Act: -0.1700
Data Index: 8344972 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9124. Min Range: -5.9124
Max Act: 5.2874. Min Act: -0.1700
Data Index: 3074974 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #19