Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2695 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4167. Min Range: -4.4167
Max Act: 4.4167. Min Act: -0.1700
Data Index: 5816192 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4167. Min Range: -4.4167
Max Act: 4.3854. Min Act: -0.1700
Data Index: 5816164 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4167. Min Range: -4.4167
Max Act: 4.3542. Min Act: -0.1700
Data Index: 5816179 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4167. Min Range: -4.4167
Max Act: 4.2604. Min Act: -0.1700
Data Index: 5816168 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4167. Min Range: -4.4167
Max Act: 4.2292. Min Act: -0.1700
Data Index: 5816163 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4167. Min Range: -4.4167
Max Act: 4.2292. Min Act: -0.1700
Data Index: 5523452 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4167. Min Range: -4.4167
Max Act: 4.1667. Min Act: -0.1700
Data Index: 5816178 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4167. Min Range: -4.4167
Max Act: 4.1667. Min Act: -0.1700
Data Index: 5816182 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4167. Min Range: -4.4167
Max Act: 4.1667. Min Act: -0.1700
Data Index: 3874705 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4167. Min Range: -4.4167
Max Act: 4.1667. Min Act: -0.1700
Data Index: 3837767 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4167. Min Range: -4.4167
Max Act: 4.1041. Min Act: -0.1700
Data Index: 4559293 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4167. Min Range: -4.4167
Max Act: 4.0729. Min Act: -0.1700
Data Index: 5816185 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4167. Min Range: -4.4167
Max Act: 4.0729. Min Act: -0.1700
Data Index: 5816169 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4167. Min Range: -4.4167
Max Act: 4.0416. Min Act: -0.1700
Data Index: 5816186 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4167. Min Range: -4.4167
Max Act: 4.0416. Min Act: -0.1700
Data Index: 5816187 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4167. Min Range: -4.4167
Max Act: 4.0416. Min Act: -0.1700
Data Index: 3331081 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4167. Min Range: -4.4167
Max Act: 4.0416. Min Act: -0.1700
Data Index: 5816166 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4167. Min Range: -4.4167
Max Act: 4.0104. Min Act: -0.1700
Data Index: 6950853 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4167. Min Range: -4.4167
Max Act: 4.0104. Min Act: -0.1700
Data Index: 3182433 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4167. Min Range: -4.4167
Max Act: 4.0104. Min Act: -0.1700
Data Index: 3546316 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #19