Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2073 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8451. Min Range: -5.8451
Max Act: 5.8451. Min Act: -0.1700
Data Index: 4792499 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8451. Min Range: -5.8451
Max Act: 5.8139. Min Act: -0.1700
Data Index: 1056625 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8451. Min Range: -5.8451
Max Act: 5.7826. Min Act: -0.1700
Data Index: 6904023 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8451. Min Range: -5.8451
Max Act: 5.7826. Min Act: -0.1700
Data Index: 653928 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8451. Min Range: -5.8451
Max Act: 5.7514. Min Act: -0.1700
Data Index: 4103858 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8451. Min Range: -5.8451
Max Act: 5.7201. Min Act: -0.1700
Data Index: 2368685 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8451. Min Range: -5.8451
Max Act: 5.7201. Min Act: -0.1700
Data Index: 7092262 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8451. Min Range: -5.8451
Max Act: 5.6889. Min Act: -0.1700
Data Index: 2829856 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8451. Min Range: -5.8451
Max Act: 5.6889. Min Act: -0.1700
Data Index: 656370 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8451. Min Range: -5.8451
Max Act: 5.7201. Min Act: -0.1700
Data Index: 6918529 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8451. Min Range: -5.8451
Max Act: 5.6889. Min Act: -0.1700
Data Index: 7353618 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8451. Min Range: -5.8451
Max Act: 5.6576. Min Act: -0.1700
Data Index: 6199140 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8451. Min Range: -5.8451
Max Act: 5.6576. Min Act: -0.1700
Data Index: 6532182 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8451. Min Range: -5.8451
Max Act: 5.6264. Min Act: -0.1700
Data Index: 7694455 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8451. Min Range: -5.8451
Max Act: 5.6576. Min Act: -0.1700
Data Index: 7409460 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8451. Min Range: -5.8451
Max Act: 5.6576. Min Act: -0.1700
Data Index: 8620727 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8451. Min Range: -5.8451
Max Act: 5.6576. Min Act: -0.1699
Data Index: 2043245 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8451. Min Range: -5.8451
Max Act: 5.6576. Min Act: -0.1700
Data Index: 4759331 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8451. Min Range: -5.8451
Max Act: 5.6576. Min Act: -0.1700
Data Index: 3512190 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8451. Min Range: -5.8451
Max Act: 5.6576. Min Act: -0.1700
Data Index: 4851780 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #19