Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3186 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9597. Min Range: -3.9597
Max Act: 3.9597. Min Act: -0.1700
Data Index: 5459679 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9597. Min Range: -3.9597
Max Act: 3.7721. Min Act: -0.1700
Data Index: 257475 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9597. Min Range: -3.9597
Max Act: 3.7095. Min Act: -0.1700
Data Index: 1773700 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9597. Min Range: -3.9597
Max Act: 3.7095. Min Act: -0.1700
Data Index: 8545296 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9597. Min Range: -3.9597
Max Act: 3.7252. Min Act: -0.1700
Data Index: 8778578 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9597. Min Range: -3.9597
Max Act: 3.7095. Min Act: -0.1700
Data Index: 8457493 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9597. Min Range: -3.9597
Max Act: 3.6939. Min Act: -0.1700
Data Index: 2219777 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9597. Min Range: -3.9597
Max Act: 3.7095. Min Act: -0.1700
Data Index: 3822191 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9597. Min Range: -3.9597
Max Act: 3.6626. Min Act: -0.1700
Data Index: 2906546 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9597. Min Range: -3.9597
Max Act: 3.6626. Min Act: -0.1700
Data Index: 759962 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9597. Min Range: -3.9597
Max Act: 3.6626. Min Act: -0.1700
Data Index: 5836332 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9597. Min Range: -3.9597
Max Act: 3.6470. Min Act: -0.1700
Data Index: 8634020 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9597. Min Range: -3.9597
Max Act: 3.6470. Min Act: -0.1700
Data Index: 829626 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9597. Min Range: -3.9597
Max Act: 3.6626. Min Act: -0.1700
Data Index: 7581759 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9597. Min Range: -3.9597
Max Act: 3.6470. Min Act: -0.1700
Data Index: 8600177 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9597. Min Range: -3.9597
Max Act: 3.6313. Min Act: -0.1700
Data Index: 5484297 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9597. Min Range: -3.9597
Max Act: 3.6313. Min Act: -0.1700
Data Index: 5627152 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9597. Min Range: -3.9597
Max Act: 3.6470. Min Act: -0.1700
Data Index: 5089946 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9597. Min Range: -3.9597
Max Act: 3.6157. Min Act: -0.1700
Data Index: 4044492 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9597. Min Range: -3.9597
Max Act: 3.6157. Min Act: -0.1700
Data Index: 2624100 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #19