Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4570 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4198. Min Range: -5.4198
Max Act: 5.4198. Min Act: -0.1700
Data Index: 8287992 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4198. Min Range: -5.4198
Max Act: 5.4198. Min Act: -0.1700
Data Index: 8643858 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4198. Min Range: -5.4198
Max Act: 5.3886. Min Act: -0.1700
Data Index: 8288009 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4198. Min Range: -5.4198
Max Act: 5.3261. Min Act: -0.1700
Data Index: 4815553 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4198. Min Range: -5.4198
Max Act: 5.2636. Min Act: -0.1700
Data Index: 4405944 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4198. Min Range: -5.4198
Max Act: 5.2323. Min Act: -0.1700
Data Index: 2969271 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4198. Min Range: -5.4198
Max Act: 5.2011. Min Act: -0.1700
Data Index: 5770369 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4198. Min Range: -5.4198
Max Act: 5.1698. Min Act: -0.1700
Data Index: 5770348 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4198. Min Range: -5.4198
Max Act: 5.1073. Min Act: -0.1700
Data Index: 8748856 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4198. Min Range: -5.4198
Max Act: 5.1386. Min Act: -0.1700
Data Index: 5770382 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4198. Min Range: -5.4198
Max Act: 5.1386. Min Act: -0.1700
Data Index: 5770368 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4198. Min Range: -5.4198
Max Act: 5.0761. Min Act: -0.1700
Data Index: 5931852 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4198. Min Range: -5.4198
Max Act: 5.1073. Min Act: -0.1700
Data Index: 4405947 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4198. Min Range: -5.4198
Max Act: 5.0761. Min Act: -0.1700
Data Index: 6952164 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4198. Min Range: -5.4198
Max Act: 5.0761. Min Act: -0.1700
Data Index: 8748857 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4198. Min Range: -5.4198
Max Act: 5.0448. Min Act: -0.1700
Data Index: 4815554 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4198. Min Range: -5.4198
Max Act: 5.0761. Min Act: -0.1700
Data Index: 8695559 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4198. Min Range: -5.4198
Max Act: 5.0448. Min Act: -0.1700
Data Index: 8287991 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4198. Min Range: -5.4198
Max Act: 5.0448. Min Act: -0.1700
Data Index: 1063442 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4198. Min Range: -5.4198
Max Act: 5.0448. Min Act: -0.1700
Data Index: 5770372 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #19