Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 51 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7366. Min Range: -6.7366
Max Act: 6.7366. Min Act: -0.1700
Data Index: 6706691 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7366. Min Range: -6.7366
Max Act: 6.7054. Min Act: -0.1700
Data Index: 6299305 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7366. Min Range: -6.7366
Max Act: 6.5491. Min Act: -0.1700
Data Index: 177123 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7366. Min Range: -6.7366
Max Act: 6.5179. Min Act: -0.1700
Data Index: 7411671 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7366. Min Range: -6.7366
Max Act: 6.4866. Min Act: -0.1700
Data Index: 8012287 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7366. Min Range: -6.7366
Max Act: 6.3929. Min Act: -0.1700
Data Index: 8126918 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7366. Min Range: -6.7366
Max Act: 6.3929. Min Act: -0.1700
Data Index: 753632 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7366. Min Range: -6.7366
Max Act: 6.3929. Min Act: -0.1700
Data Index: 6763744 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7366. Min Range: -6.7366
Max Act: 6.3616. Min Act: -0.1700
Data Index: 6492617 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7366. Min Range: -6.7366
Max Act: 6.3304. Min Act: -0.1700
Data Index: 5167556 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7366. Min Range: -6.7366
Max Act: 6.2991. Min Act: -0.1700
Data Index: 7684717 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7366. Min Range: -6.7366
Max Act: 6.2679. Min Act: -0.1700
Data Index: 5731191 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7366. Min Range: -6.7366
Max Act: 6.2991. Min Act: -0.1700
Data Index: 463453 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7366. Min Range: -6.7366
Max Act: 6.2679. Min Act: -0.1700
Data Index: 1369582 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7366. Min Range: -6.7366
Max Act: 6.2991. Min Act: -0.1700
Data Index: 6154614 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7366. Min Range: -6.7366
Max Act: 6.2366. Min Act: -0.1700
Data Index: 8244170 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7366. Min Range: -6.7366
Max Act: 6.2054. Min Act: -0.1700
Data Index: 3055546 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7366. Min Range: -6.7366
Max Act: 6.2054. Min Act: -0.1700
Data Index: 3211337 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7366. Min Range: -6.7366
Max Act: 6.1741. Min Act: -0.1700
Data Index: 1521419 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7366. Min Range: -6.7366
Max Act: 6.2054. Min Act: -0.1700
Data Index: 5735227 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #19