Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2564 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4904. Min Range: -5.4904
Max Act: 5.4904. Min Act: -0.1700
Data Index: 5679760 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4904. Min Range: -5.4904
Max Act: 5.2404. Min Act: -0.1700
Data Index: 2065171 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4904. Min Range: -5.4904
Max Act: 5.1779. Min Act: -0.1700
Data Index: 3817590 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4904. Min Range: -5.4904
Max Act: 5.1779. Min Act: -0.1700
Data Index: 6364337 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4904. Min Range: -5.4904
Max Act: 5.1154. Min Act: -0.1700
Data Index: 7272461 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4904. Min Range: -5.4904
Max Act: 5.1466. Min Act: -0.1700
Data Index: 969971 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4904. Min Range: -5.4904
Max Act: 5.1154. Min Act: -0.1700
Data Index: 7030586 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4904. Min Range: -5.4904
Max Act: 5.1154. Min Act: -0.1700
Data Index: 6361177 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4904. Min Range: -5.4904
Max Act: 5.1154. Min Act: -0.1700
Data Index: 6212623 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4904. Min Range: -5.4904
Max Act: 5.0841. Min Act: -0.1700
Data Index: 4748224 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4904. Min Range: -5.4904
Max Act: 5.0841. Min Act: -0.1700
Data Index: 8695778 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4904. Min Range: -5.4904
Max Act: 5.0841. Min Act: -0.1700
Data Index: 441388 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4904. Min Range: -5.4904
Max Act: 5.0841. Min Act: -0.1700
Data Index: 5941824 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4904. Min Range: -5.4904
Max Act: 5.0841. Min Act: -0.1700
Data Index: 7580716 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4904. Min Range: -5.4904
Max Act: 5.0529. Min Act: -0.1700
Data Index: 3912225 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4904. Min Range: -5.4904
Max Act: 5.0841. Min Act: -0.1700
Data Index: 2120603 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4904. Min Range: -5.4904
Max Act: 5.0529. Min Act: -0.1700
Data Index: 3829321 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4904. Min Range: -5.4904
Max Act: 5.0216. Min Act: -0.1700
Data Index: 686873 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4904. Min Range: -5.4904
Max Act: 5.0216. Min Act: -0.1700
Data Index: 4875201 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4904. Min Range: -5.4904
Max Act: 5.0216. Min Act: -0.1700
Data Index: 2588036 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #19