Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3456 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3547. Min Range: -4.3547
Max Act: 4.3547. Min Act: -0.1700
Data Index: 8045718 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3547. Min Range: -4.3547
Max Act: 4.0422. Min Act: -0.1700
Data Index: 8203936 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3547. Min Range: -4.3547
Max Act: 4.0109. Min Act: -0.1700
Data Index: 2255885 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3547. Min Range: -4.3547
Max Act: 3.9172. Min Act: -0.1700
Data Index: 8544471 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3547. Min Range: -4.3547
Max Act: 3.8859. Min Act: -0.1700
Data Index: 3108700 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3547. Min Range: -4.3547
Max Act: 3.8859. Min Act: -0.1700
Data Index: 9699 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3547. Min Range: -4.3547
Max Act: 3.8703. Min Act: -0.1700
Data Index: 2867503 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3547. Min Range: -4.3547
Max Act: 3.8234. Min Act: -0.1700
Data Index: 2605456 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3547. Min Range: -4.3547
Max Act: 3.7921. Min Act: -0.1700
Data Index: 4673243 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3547. Min Range: -4.3547
Max Act: 3.7921. Min Act: -0.1700
Data Index: 7785464 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3547. Min Range: -4.3547
Max Act: 3.7764. Min Act: -0.1700
Data Index: 4885630 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3547. Min Range: -4.3547
Max Act: 3.7608. Min Act: -0.1700
Data Index: 4986283 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3547. Min Range: -4.3547
Max Act: 3.7452. Min Act: -0.1700
Data Index: 8113592 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3547. Min Range: -4.3547
Max Act: 3.7608. Min Act: -0.1700
Data Index: 2113806 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3547. Min Range: -4.3547
Max Act: 3.7295. Min Act: -0.1700
Data Index: 8450787 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3547. Min Range: -4.3547
Max Act: 3.7295. Min Act: -0.1700
Data Index: 4781444 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3547. Min Range: -4.3547
Max Act: 3.7295. Min Act: -0.1700
Data Index: 8072940 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3547. Min Range: -4.3547
Max Act: 3.7452. Min Act: -0.1700
Data Index: 4775869 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3547. Min Range: -4.3547
Max Act: 3.7295. Min Act: -0.1700
Data Index: 7468108 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3547. Min Range: -4.3547
Max Act: 3.7608. Min Act: -0.1700
Data Index: 4657880 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #19