Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3410 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0545. Min Range: -3.0545
Max Act: 3.0545. Min Act: -0.1700
Data Index: 7844438 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0545. Min Range: -3.0545
Max Act: 3.0071. Min Act: -0.1700
Data Index: 1012581 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0545. Min Range: -3.0545
Max Act: 2.9913. Min Act: -0.1700
Data Index: 2647238 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0545. Min Range: -3.0545
Max Act: 2.9755. Min Act: -0.1700
Data Index: 7394120 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0545. Min Range: -3.0545
Max Act: 2.9280. Min Act: -0.1700
Data Index: 3810970 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0545. Min Range: -3.0545
Max Act: 2.9280. Min Act: -0.1700
Data Index: 2278807 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0545. Min Range: -3.0545
Max Act: 2.9122. Min Act: -0.1700
Data Index: 4127004 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0545. Min Range: -3.0545
Max Act: 2.8963. Min Act: -0.1700
Data Index: 7827327 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0545. Min Range: -3.0545
Max Act: 2.8646. Min Act: -0.1700
Data Index: 104045 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0545. Min Range: -3.0545
Max Act: 2.8805. Min Act: -0.1700
Data Index: 5660708 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0545. Min Range: -3.0545
Max Act: 2.8646. Min Act: -0.1700
Data Index: 3076752 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0545. Min Range: -3.0545
Max Act: 2.8646. Min Act: -0.1700
Data Index: 3810969 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0545. Min Range: -3.0545
Max Act: 2.8646. Min Act: -0.1700
Data Index: 5858701 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0545. Min Range: -3.0545
Max Act: 2.8646. Min Act: -0.1700
Data Index: 8211843 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0545. Min Range: -3.0545
Max Act: 2.8487. Min Act: -0.1700
Data Index: 3128380 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0545. Min Range: -3.0545
Max Act: 2.8328. Min Act: -0.1700
Data Index: 1321581 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0545. Min Range: -3.0545
Max Act: 2.8328. Min Act: -0.1700
Data Index: 1876689 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0545. Min Range: -3.0545
Max Act: 2.8328. Min Act: -0.1700
Data Index: 6352578 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0545. Min Range: -3.0545
Max Act: 2.8328. Min Act: -0.1700
Data Index: 6533670 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0545. Min Range: -3.0545
Max Act: 2.8169. Min Act: -0.1700
Data Index: 4759221 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #19