Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3424 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0450. Min Range: -7.0450
Max Act: 7.0450. Min Act: -0.1700
Data Index: 4941250 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0450. Min Range: -7.0450
Max Act: 6.9825. Min Act: -0.1700
Data Index: 5581382 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0450. Min Range: -7.0450
Max Act: 6.8575. Min Act: -0.1700
Data Index: 3288278 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0450. Min Range: -7.0450
Max Act: 6.7950. Min Act: -0.1700
Data Index: 1798118 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0450. Min Range: -7.0450
Max Act: 6.7637. Min Act: -0.1700
Data Index: 4125652 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0450. Min Range: -7.0450
Max Act: 6.7637. Min Act: -0.1700
Data Index: 58620 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0450. Min Range: -7.0450
Max Act: 6.7950. Min Act: -0.1700
Data Index: 1250001 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0450. Min Range: -7.0450
Max Act: 6.7325. Min Act: -0.1700
Data Index: 3024229 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0450. Min Range: -7.0450
Max Act: 6.7325. Min Act: -0.1700
Data Index: 7488272 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0450. Min Range: -7.0450
Max Act: 6.6700. Min Act: -0.1700
Data Index: 4228022 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0450. Min Range: -7.0450
Max Act: 6.6700. Min Act: -0.1700
Data Index: 1430960 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0450. Min Range: -7.0450
Max Act: 6.7325. Min Act: -0.1700
Data Index: 5887587 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0450. Min Range: -7.0450
Max Act: 6.6700. Min Act: -0.1700
Data Index: 6499772 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0450. Min Range: -7.0450
Max Act: 6.6387. Min Act: -0.1700
Data Index: 4127585 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0450. Min Range: -7.0450
Max Act: 6.6387. Min Act: -0.1700
Data Index: 8665647 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0450. Min Range: -7.0450
Max Act: 6.6075. Min Act: -0.1700
Data Index: 4166088 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0450. Min Range: -7.0450
Max Act: 6.6387. Min Act: -0.1700
Data Index: 6086187 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0450. Min Range: -7.0450
Max Act: 6.6700. Min Act: -0.1700
Data Index: 505568 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0450. Min Range: -7.0450
Max Act: 6.6075. Min Act: -0.1700
Data Index: 8588257 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0450. Min Range: -7.0450
Max Act: 6.5762. Min Act: -0.1700
Data Index: 2117849 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #19