Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4461 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6874. Min Range: -6.6874
Max Act: 6.6874. Min Act: -0.1700
Data Index: 7642969 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6874. Min Range: -6.6874
Max Act: 6.6874. Min Act: -0.1700
Data Index: 6313624 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6874. Min Range: -6.6874
Max Act: 6.5936. Min Act: -0.1700
Data Index: 6026154 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6874. Min Range: -6.6874
Max Act: 6.5624. Min Act: -0.1700
Data Index: 1645289 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6874. Min Range: -6.6874
Max Act: 6.5311. Min Act: -0.1700
Data Index: 8607480 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6874. Min Range: -6.6874
Max Act: 6.4686. Min Act: -0.1700
Data Index: 6129053 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6874. Min Range: -6.6874
Max Act: 6.4999. Min Act: -0.1700
Data Index: 8504094 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6874. Min Range: -6.6874
Max Act: 6.4374. Min Act: -0.1700
Data Index: 1737260 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6874. Min Range: -6.6874
Max Act: 6.4686. Min Act: -0.1700
Data Index: 5867424 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6874. Min Range: -6.6874
Max Act: 6.4374. Min Act: -0.1700
Data Index: 70137 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6874. Min Range: -6.6874
Max Act: 6.4374. Min Act: -0.1700
Data Index: 2632834 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6874. Min Range: -6.6874
Max Act: 6.3749. Min Act: -0.1700
Data Index: 7985901 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6874. Min Range: -6.6874
Max Act: 6.4061. Min Act: -0.1700
Data Index: 909490 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6874. Min Range: -6.6874
Max Act: 6.4061. Min Act: -0.1700
Data Index: 2729434 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6874. Min Range: -6.6874
Max Act: 6.3436. Min Act: -0.1700
Data Index: 909494 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6874. Min Range: -6.6874
Max Act: 6.3436. Min Act: -0.1700
Data Index: 5254352 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6874. Min Range: -6.6874
Max Act: 6.2811. Min Act: -0.1700
Data Index: 7899437 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6874. Min Range: -6.6874
Max Act: 6.3124. Min Act: -0.1700
Data Index: 3125650 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6874. Min Range: -6.6874
Max Act: 6.3124. Min Act: -0.1700
Data Index: 6643900 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6874. Min Range: -6.6874
Max Act: 6.3124. Min Act: -0.1700
Data Index: 4860470 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #19