Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2041 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5942. Min Range: -5.5942
Max Act: 5.5942. Min Act: -0.1700
Data Index: 4034270 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5942. Min Range: -5.5942
Max Act: 5.4692. Min Act: -0.1700
Data Index: 6341410 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5942. Min Range: -5.5942
Max Act: 5.4067. Min Act: -0.1700
Data Index: 184309 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5942. Min Range: -5.5942
Max Act: 5.3442. Min Act: -0.1700
Data Index: 70968 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5942. Min Range: -5.5942
Max Act: 5.2505. Min Act: -0.1700
Data Index: 793275 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5942. Min Range: -5.5942
Max Act: 5.2817. Min Act: -0.1700
Data Index: 8398749 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5942. Min Range: -5.5942
Max Act: 5.2192. Min Act: -0.1700
Data Index: 6238925 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5942. Min Range: -5.5942
Max Act: 5.1880. Min Act: -0.1700
Data Index: 6023506 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5942. Min Range: -5.5942
Max Act: 5.1880. Min Act: -0.1700
Data Index: 5981429 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5942. Min Range: -5.5942
Max Act: 5.1567. Min Act: -0.1700
Data Index: 7177418 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5942. Min Range: -5.5942
Max Act: 5.1567. Min Act: -0.1700
Data Index: 3833556 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5942. Min Range: -5.5942
Max Act: 5.1255. Min Act: -0.1700
Data Index: 6070188 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5942. Min Range: -5.5942
Max Act: 5.1255. Min Act: -0.1700
Data Index: 4782526 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5942. Min Range: -5.5942
Max Act: 5.1255. Min Act: -0.1700
Data Index: 5598698 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5942. Min Range: -5.5942
Max Act: 5.1255. Min Act: -0.1700
Data Index: 8019432 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5942. Min Range: -5.5942
Max Act: 5.1255. Min Act: -0.1700
Data Index: 3862209 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5942. Min Range: -5.5942
Max Act: 5.0942. Min Act: -0.1700
Data Index: 2433070 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5942. Min Range: -5.5942
Max Act: 5.0942. Min Act: -0.1700
Data Index: 7490960 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5942. Min Range: -5.5942
Max Act: 5.0942. Min Act: -0.1700
Data Index: 3118900 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5942. Min Range: -5.5942
Max Act: 5.0942. Min Act: -0.1700
Data Index: 3226728 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #19