Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4852 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8171. Min Range: -3.8171
Max Act: 3.8171. Min Act: -0.1700
Data Index: 5703560 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8171. Min Range: -3.8171
Max Act: 3.7233. Min Act: -0.1700
Data Index: 1109194 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8171. Min Range: -3.8171
Max Act: 3.7233. Min Act: -0.1700
Data Index: 7499919 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8171. Min Range: -3.8171
Max Act: 3.7077. Min Act: -0.1700
Data Index: 1902944 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8171. Min Range: -3.8171
Max Act: 3.6920. Min Act: -0.1700
Data Index: 8172673 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8171. Min Range: -3.8171
Max Act: 3.6764. Min Act: -0.1700
Data Index: 4115161 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8171. Min Range: -3.8171
Max Act: 3.6764. Min Act: -0.1700
Data Index: 2262333 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8171. Min Range: -3.8171
Max Act: 3.6607. Min Act: -0.1700
Data Index: 2064657 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8171. Min Range: -3.8171
Max Act: 3.6607. Min Act: -0.1700
Data Index: 3198974 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8171. Min Range: -3.8171
Max Act: 3.6607. Min Act: -0.1700
Data Index: 7945283 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8171. Min Range: -3.8171
Max Act: 3.6607. Min Act: -0.1700
Data Index: 5775316 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8171. Min Range: -3.8171
Max Act: 3.6451. Min Act: -0.1700
Data Index: 8540609 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8171. Min Range: -3.8171
Max Act: 3.6138. Min Act: -0.1700
Data Index: 5607658 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8171. Min Range: -3.8171
Max Act: 3.6294. Min Act: -0.1700
Data Index: 7012551 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8171. Min Range: -3.8171
Max Act: 3.6294. Min Act: -0.1700
Data Index: 6841551 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8171. Min Range: -3.8171
Max Act: 3.6138. Min Act: -0.1700
Data Index: 256189 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8171. Min Range: -3.8171
Max Act: 3.6138. Min Act: -0.1700
Data Index: 6673058 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8171. Min Range: -3.8171
Max Act: 3.6138. Min Act: -0.1700
Data Index: 33385 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8171. Min Range: -3.8171
Max Act: 3.6138. Min Act: -0.1700
Data Index: 6845603 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8171. Min Range: -3.8171
Max Act: 3.5981. Min Act: -0.1700
Data Index: 3619295 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #19