Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1906 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1796. Min Range: -4.1796
Max Act: 4.1796. Min Act: -0.1700
Data Index: 5891690 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1796. Min Range: -4.1796
Max Act: 4.0546. Min Act: -0.1700
Data Index: 1487490 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1796. Min Range: -4.1796
Max Act: 4.0546. Min Act: -0.1700
Data Index: 3298272 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1796. Min Range: -4.1796
Max Act: 4.0858. Min Act: -0.1700
Data Index: 7646330 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1796. Min Range: -4.1796
Max Act: 4.0546. Min Act: -0.1700
Data Index: 3177871 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1796. Min Range: -4.1796
Max Act: 4.0233. Min Act: -0.1700
Data Index: 7823918 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1796. Min Range: -4.1796
Max Act: 3.9920. Min Act: -0.1700
Data Index: 4265690 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1796. Min Range: -4.1796
Max Act: 4.0233. Min Act: -0.1700
Data Index: 5647255 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1796. Min Range: -4.1796
Max Act: 4.0233. Min Act: -0.1700
Data Index: 2185405 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1796. Min Range: -4.1796
Max Act: 3.9920. Min Act: -0.1700
Data Index: 3548959 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1796. Min Range: -4.1796
Max Act: 3.9920. Min Act: -0.1700
Data Index: 5360341 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1796. Min Range: -4.1796
Max Act: 3.9920. Min Act: -0.1700
Data Index: 4246112 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1796. Min Range: -4.1796
Max Act: 3.9608. Min Act: -0.1700
Data Index: 33194 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1796. Min Range: -4.1796
Max Act: 3.9608. Min Act: -0.1700
Data Index: 6589283 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1796. Min Range: -4.1796
Max Act: 3.9608. Min Act: -0.1700
Data Index: 6382919 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1796. Min Range: -4.1796
Max Act: 3.9920. Min Act: -0.1700
Data Index: 2262506 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1796. Min Range: -4.1796
Max Act: 3.9295. Min Act: -0.1700
Data Index: 2834801 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1796. Min Range: -4.1796
Max Act: 3.9295. Min Act: -0.1700
Data Index: 5651261 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1796. Min Range: -4.1796
Max Act: 3.9295. Min Act: -0.1700
Data Index: 5788718 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1796. Min Range: -4.1796
Max Act: 3.9295. Min Act: -0.1700
Data Index: 4191610 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #19