Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5004 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9415. Min Range: -5.9415
Max Act: 5.9415. Min Act: -0.1700
Data Index: 5765496 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9415. Min Range: -5.9415
Max Act: 5.8790. Min Act: -0.1700
Data Index: 1324503 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9415. Min Range: -5.9415
Max Act: 5.8790. Min Act: -0.1700
Data Index: 1847534 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9415. Min Range: -5.9415
Max Act: 5.8477. Min Act: -0.1700
Data Index: 4181838 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9415. Min Range: -5.9415
Max Act: 5.8165. Min Act: -0.1700
Data Index: 6384603 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9415. Min Range: -5.9415
Max Act: 5.7540. Min Act: -0.1700
Data Index: 180951 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9415. Min Range: -5.9415
Max Act: 5.7540. Min Act: -0.1700
Data Index: 1938270 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9415. Min Range: -5.9415
Max Act: 5.7540. Min Act: -0.1700
Data Index: 8424122 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9415. Min Range: -5.9415
Max Act: 5.7852. Min Act: -0.1700
Data Index: 3425277 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9415. Min Range: -5.9415
Max Act: 5.7540. Min Act: -0.1700
Data Index: 4018045 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9415. Min Range: -5.9415
Max Act: 5.7227. Min Act: -0.1700
Data Index: 2713732 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9415. Min Range: -5.9415
Max Act: 5.7227. Min Act: -0.1700
Data Index: 4744800 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9415. Min Range: -5.9415
Max Act: 5.6915. Min Act: -0.1700
Data Index: 101365 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9415. Min Range: -5.9415
Max Act: 5.6290. Min Act: -0.1700
Data Index: 8323652 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9415. Min Range: -5.9415
Max Act: 5.6290. Min Act: -0.1700
Data Index: 4633349 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9415. Min Range: -5.9415
Max Act: 5.5977. Min Act: -0.1700
Data Index: 5636128 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9415. Min Range: -5.9415
Max Act: 5.5977. Min Act: -0.1700
Data Index: 7060884 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9415. Min Range: -5.9415
Max Act: 5.5977. Min Act: -0.1700
Data Index: 5028051 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9415. Min Range: -5.9415
Max Act: 5.5665. Min Act: -0.1700
Data Index: 7109879 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9415. Min Range: -5.9415
Max Act: 5.5665. Min Act: -0.1700
Data Index: 8414820 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #19