Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5733 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3652. Min Range: -5.3652
Max Act: 5.3652. Min Act: -0.1700
Data Index: 2748042 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3652. Min Range: -5.3652
Max Act: 5.3340. Min Act: -0.1700
Data Index: 3642618 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3652. Min Range: -5.3652
Max Act: 5.2402. Min Act: -0.1700
Data Index: 4950141 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3652. Min Range: -5.3652
Max Act: 5.2715. Min Act: -0.1700
Data Index: 2325490 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3652. Min Range: -5.3652
Max Act: 5.1777. Min Act: -0.1700
Data Index: 7545610 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3652. Min Range: -5.3652
Max Act: 5.1465. Min Act: -0.1700
Data Index: 5735064 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3652. Min Range: -5.3652
Max Act: 5.1465. Min Act: -0.1700
Data Index: 5735066 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3652. Min Range: -5.3652
Max Act: 5.1465. Min Act: -0.1700
Data Index: 954328 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3652. Min Range: -5.3652
Max Act: 5.0527. Min Act: -0.1700
Data Index: 8140375 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3652. Min Range: -5.3652
Max Act: 5.0527. Min Act: -0.1700
Data Index: 8169795 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3652. Min Range: -5.3652
Max Act: 5.0215. Min Act: -0.1700
Data Index: 901145 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3652. Min Range: -5.3652
Max Act: 4.9277. Min Act: -0.1700
Data Index: 6778358 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3652. Min Range: -5.3652
Max Act: 4.9590. Min Act: -0.1700
Data Index: 866058 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3652. Min Range: -5.3652
Max Act: 4.9590. Min Act: -0.1700
Data Index: 1320446 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3652. Min Range: -5.3652
Max Act: 4.9277. Min Act: -0.1700
Data Index: 1869473 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3652. Min Range: -5.3652
Max Act: 4.9277. Min Act: -0.1700
Data Index: 4798122 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3652. Min Range: -5.3652
Max Act: 4.9277. Min Act: -0.1700
Data Index: 4339203 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3652. Min Range: -5.3652
Max Act: 4.8965. Min Act: -0.1700
Data Index: 4250692 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3652. Min Range: -5.3652
Max Act: 4.8965. Min Act: -0.1700
Data Index: 4042845 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3652. Min Range: -5.3652
Max Act: 4.8965. Min Act: -0.1700
Data Index: 7782638 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #19