Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2801 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5862. Min Range: -3.5862
Max Act: 3.5862. Min Act: -0.1700
Data Index: 1295948 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5862. Min Range: -3.5862
Max Act: 3.5862. Min Act: -0.1700
Data Index: 5200000 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5862. Min Range: -3.5862
Max Act: 3.5862. Min Act: -0.1700
Data Index: 5694131 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5862. Min Range: -3.5862
Max Act: 3.5549. Min Act: -0.1700
Data Index: 1057735 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5862. Min Range: -3.5862
Max Act: 3.5549. Min Act: -0.1700
Data Index: 1711480 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5862. Min Range: -3.5862
Max Act: 3.5235. Min Act: -0.1700
Data Index: 8301419 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5862. Min Range: -3.5862
Max Act: 3.5235. Min Act: -0.1700
Data Index: 733459 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5862. Min Range: -3.5862
Max Act: 3.5235. Min Act: -0.1700
Data Index: 1057734 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5862. Min Range: -3.5862
Max Act: 3.5235. Min Act: -0.1700
Data Index: 2976726 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5862. Min Range: -3.5862
Max Act: 3.5235. Min Act: -0.1700
Data Index: 6358811 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5862. Min Range: -3.5862
Max Act: 3.5235. Min Act: -0.1700
Data Index: 5887538 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5862. Min Range: -3.5862
Max Act: 3.5235. Min Act: -0.1700
Data Index: 5776008 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5862. Min Range: -3.5862
Max Act: 3.5235. Min Act: -0.1700
Data Index: 510318 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5862. Min Range: -3.5862
Max Act: 3.5235. Min Act: -0.1700
Data Index: 2613870 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5862. Min Range: -3.5862
Max Act: 3.5235. Min Act: -0.1700
Data Index: 2543018 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5862. Min Range: -3.5862
Max Act: 3.4922. Min Act: -0.1700
Data Index: 3381182 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5862. Min Range: -3.5862
Max Act: 3.4922. Min Act: -0.1700
Data Index: 1173574 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5862. Min Range: -3.5862
Max Act: 3.4922. Min Act: -0.1700
Data Index: 3466082 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5862. Min Range: -3.5862
Max Act: 3.4922. Min Act: -0.1700
Data Index: 3467580 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5862. Min Range: -3.5862
Max Act: 3.4922. Min Act: -0.1700
Data Index: 3673822 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #19