Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4488 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0726. Min Range: -6.0726
Max Act: 6.0726. Min Act: -0.1700
Data Index: 3406913 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0726. Min Range: -6.0726
Max Act: 5.9476. Min Act: -0.1700
Data Index: 846261 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0726. Min Range: -6.0726
Max Act: 5.9163. Min Act: -0.1700
Data Index: 4560597 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0726. Min Range: -6.0726
Max Act: 5.9163. Min Act: -0.1700
Data Index: 892989 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0726. Min Range: -6.0726
Max Act: 5.8851. Min Act: -0.1700
Data Index: 1357943 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0726. Min Range: -6.0726
Max Act: 5.8851. Min Act: -0.1700
Data Index: 7743659 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0726. Min Range: -6.0726
Max Act: 5.8851. Min Act: -0.1700
Data Index: 5837678 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0726. Min Range: -6.0726
Max Act: 5.8538. Min Act: -0.1700
Data Index: 2249668 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0726. Min Range: -6.0726
Max Act: 5.8538. Min Act: -0.1700
Data Index: 3936524 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0726. Min Range: -6.0726
Max Act: 5.8226. Min Act: -0.1700
Data Index: 290084 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0726. Min Range: -6.0726
Max Act: 5.7601. Min Act: -0.1700
Data Index: 4734315 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0726. Min Range: -6.0726
Max Act: 5.7913. Min Act: -0.1700
Data Index: 1837566 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0726. Min Range: -6.0726
Max Act: 5.7913. Min Act: -0.1700
Data Index: 5637948 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0726. Min Range: -6.0726
Max Act: 5.7288. Min Act: -0.1700
Data Index: 4971293 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0726. Min Range: -6.0726
Max Act: 5.7601. Min Act: -0.1700
Data Index: 8142363 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0726. Min Range: -6.0726
Max Act: 5.7601. Min Act: -0.1700
Data Index: 96208 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0726. Min Range: -6.0726
Max Act: 5.7601. Min Act: -0.1700
Data Index: 6488847 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0726. Min Range: -6.0726
Max Act: 5.7288. Min Act: -0.1700
Data Index: 3492714 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0726. Min Range: -6.0726
Max Act: 5.7288. Min Act: -0.1700
Data Index: 1394347 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0726. Min Range: -6.0726
Max Act: 5.7288. Min Act: -0.1700
Data Index: 976680 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #19