Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4635 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4587. Min Range: -6.4587
Max Act: 6.4587. Min Act: -0.1700
Data Index: 5225307 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4587. Min Range: -6.4587
Max Act: 6.3337. Min Act: -0.1700
Data Index: 6098720 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4587. Min Range: -6.4587
Max Act: 6.2400. Min Act: -0.1700
Data Index: 878679 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4587. Min Range: -6.4587
Max Act: 6.2400. Min Act: -0.1700
Data Index: 2285199 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4587. Min Range: -6.4587
Max Act: 6.2087. Min Act: -0.1700
Data Index: 1550657 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4587. Min Range: -6.4587
Max Act: 6.1462. Min Act: -0.1700
Data Index: 740261 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4587. Min Range: -6.4587
Max Act: 6.1150. Min Act: -0.1700
Data Index: 346146 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4587. Min Range: -6.4587
Max Act: 6.1150. Min Act: -0.1700
Data Index: 3063839 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4587. Min Range: -6.4587
Max Act: 6.0837. Min Act: -0.1700
Data Index: 958949 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4587. Min Range: -6.4587
Max Act: 6.0212. Min Act: -0.1700
Data Index: 4209429 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4587. Min Range: -6.4587
Max Act: 5.9900. Min Act: -0.1700
Data Index: 4730453 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4587. Min Range: -6.4587
Max Act: 5.9275. Min Act: -0.1700
Data Index: 3925531 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4587. Min Range: -6.4587
Max Act: 5.9587. Min Act: -0.1700
Data Index: 4720846 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4587. Min Range: -6.4587
Max Act: 5.8962. Min Act: -0.1700
Data Index: 5204153 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4587. Min Range: -6.4587
Max Act: 5.8962. Min Act: -0.1700
Data Index: 3574538 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4587. Min Range: -6.4587
Max Act: 5.8962. Min Act: -0.1700
Data Index: 3706031 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4587. Min Range: -6.4587
Max Act: 5.8962. Min Act: -0.1700
Data Index: 5059251 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4587. Min Range: -6.4587
Max Act: 5.8962. Min Act: -0.1700
Data Index: 7062542 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4587. Min Range: -6.4587
Max Act: 5.8962. Min Act: -0.1700
Data Index: 6400184 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4587. Min Range: -6.4587
Max Act: 5.8337. Min Act: -0.1700
Data Index: 2325878 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #19