Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3210 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.3874. Min Range: -10.3874
Max Act: 10.3874. Min Act: -0.1700
Data Index: 4268503 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.3874. Min Range: -10.3874
Max Act: 10.1374. Min Act: -0.1700
Data Index: 2035775 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.3874. Min Range: -10.3874
Max Act: 10.0124. Min Act: -0.1700
Data Index: 8562187 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.3874. Min Range: -10.3874
Max Act: 9.9499. Min Act: -0.1700
Data Index: 7876149 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.3874. Min Range: -10.3874
Max Act: 9.9499. Min Act: -0.1700
Data Index: 8439194 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.3874. Min Range: -10.3874
Max Act: 9.8874. Min Act: -0.1700
Data Index: 3269324 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.3874. Min Range: -10.3874
Max Act: 9.8874. Min Act: -0.1700
Data Index: 3194516 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.3874. Min Range: -10.3874
Max Act: 9.8249. Min Act: -0.1700
Data Index: 3025964 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.3874. Min Range: -10.3874
Max Act: 9.7624. Min Act: -0.1700
Data Index: 1316380 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.3874. Min Range: -10.3874
Max Act: 9.6999. Min Act: -0.1700
Data Index: 3970435 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.3874. Min Range: -10.3874
Max Act: 9.6999. Min Act: -0.1700
Data Index: 4382611 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.3874. Min Range: -10.3874
Max Act: 9.7624. Min Act: -0.1700
Data Index: 5475182 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.3874. Min Range: -10.3874
Max Act: 9.6374. Min Act: -0.1700
Data Index: 2515277 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.3874. Min Range: -10.3874
Max Act: 9.6374. Min Act: -0.1700
Data Index: 6250394 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.3874. Min Range: -10.3874
Max Act: 9.5749. Min Act: -0.1700
Data Index: 320222 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.3874. Min Range: -10.3874
Max Act: 9.5749. Min Act: -0.1700
Data Index: 5352886 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.3874. Min Range: -10.3874
Max Act: 9.5124. Min Act: -0.1700
Data Index: 703657 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.3874. Min Range: -10.3874
Max Act: 9.5124. Min Act: -0.1700
Data Index: 7544715 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.3874. Min Range: -10.3874
Max Act: 9.5124. Min Act: -0.1700
Data Index: 8379207 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.3874. Min Range: -10.3874
Max Act: 9.5124. Min Act: -0.1700
Data Index: 6862441 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #19