Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2399 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2646. Min Range: -4.2646
Max Act: 4.2646. Min Act: -0.1700
Data Index: 6227198 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2646. Min Range: -4.2646
Max Act: 4.2333. Min Act: -0.1700
Data Index: 505742 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2646. Min Range: -4.2646
Max Act: 4.0458. Min Act: -0.1700
Data Index: 1535921 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2646. Min Range: -4.2646
Max Act: 3.9833. Min Act: -0.1700
Data Index: 2933075 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2646. Min Range: -4.2646
Max Act: 3.9520. Min Act: -0.1700
Data Index: 3183505 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2646. Min Range: -4.2646
Max Act: 3.9208. Min Act: -0.1700
Data Index: 7696742 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2646. Min Range: -4.2646
Max Act: 3.9208. Min Act: -0.1700
Data Index: 3350114 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2646. Min Range: -4.2646
Max Act: 3.8895. Min Act: -0.1700
Data Index: 8288380 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2646. Min Range: -4.2646
Max Act: 3.8582. Min Act: -0.1700
Data Index: 7346199 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2646. Min Range: -4.2646
Max Act: 3.8582. Min Act: -0.1700
Data Index: 4835656 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2646. Min Range: -4.2646
Max Act: 3.7957. Min Act: -0.1700
Data Index: 2534691 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2646. Min Range: -4.2646
Max Act: 3.8582. Min Act: -0.1700
Data Index: 2350016 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2646. Min Range: -4.2646
Max Act: 3.8270. Min Act: -0.1700
Data Index: 5032035 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2646. Min Range: -4.2646
Max Act: 3.7957. Min Act: -0.1700
Data Index: 7081187 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2646. Min Range: -4.2646
Max Act: 3.7957. Min Act: -0.1700
Data Index: 6375010 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2646. Min Range: -4.2646
Max Act: 3.7957. Min Act: -0.1700
Data Index: 7564876 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2646. Min Range: -4.2646
Max Act: 3.7957. Min Act: -0.1700
Data Index: 2850466 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2646. Min Range: -4.2646
Max Act: 3.7957. Min Act: -0.1700
Data Index: 8049823 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2646. Min Range: -4.2646
Max Act: 3.7957. Min Act: -0.1700
Data Index: 6366265 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2646. Min Range: -4.2646
Max Act: 3.7644. Min Act: -0.1700
Data Index: 2534637 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #19