Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2454 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3295. Min Range: -8.3295
Max Act: 8.3295. Min Act: -0.1700
Data Index: 2547235 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3295. Min Range: -8.3295
Max Act: 8.0482. Min Act: -0.1700
Data Index: 7561389 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3295. Min Range: -8.3295
Max Act: 7.8295. Min Act: -0.1700
Data Index: 3489365 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3295. Min Range: -8.3295
Max Act: 7.7982. Min Act: -0.1700
Data Index: 1570912 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3295. Min Range: -8.3295
Max Act: 7.7357. Min Act: -0.1700
Data Index: 4667486 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3295. Min Range: -8.3295
Max Act: 7.7357. Min Act: -0.1700
Data Index: 5392310 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3295. Min Range: -8.3295
Max Act: 7.7045. Min Act: -0.1700
Data Index: 5201405 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3295. Min Range: -8.3295
Max Act: 7.6732. Min Act: -0.1700
Data Index: 1505314 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3295. Min Range: -8.3295
Max Act: 7.6420. Min Act: -0.1700
Data Index: 7928418 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3295. Min Range: -8.3295
Max Act: 7.5795. Min Act: -0.1700
Data Index: 4391435 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3295. Min Range: -8.3295
Max Act: 7.5170. Min Act: -0.1700
Data Index: 6453111 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3295. Min Range: -8.3295
Max Act: 7.5170. Min Act: -0.1700
Data Index: 4598395 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3295. Min Range: -8.3295
Max Act: 7.4857. Min Act: -0.1700
Data Index: 2891865 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3295. Min Range: -8.3295
Max Act: 7.5170. Min Act: -0.1700
Data Index: 1409969 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3295. Min Range: -8.3295
Max Act: 7.4857. Min Act: -0.1700
Data Index: 1422951 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3295. Min Range: -8.3295
Max Act: 7.4545. Min Act: -0.1700
Data Index: 148981 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3295. Min Range: -8.3295
Max Act: 7.4232. Min Act: -0.1700
Data Index: 770253 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3295. Min Range: -8.3295
Max Act: 7.3607. Min Act: -0.1700
Data Index: 573582 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3295. Min Range: -8.3295
Max Act: 7.4232. Min Act: -0.1700
Data Index: 6148580 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3295. Min Range: -8.3295
Max Act: 7.4232. Min Act: -0.1700
Data Index: 4330073 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #19