Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2665 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.5791. Min Range: -2.5791
Max Act: 2.5791. Min Act: -0.1700
Data Index: 3551410 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5791. Min Range: -2.5791
Max Act: 2.5468. Min Act: -0.1700
Data Index: 5737111 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5791. Min Range: -2.5791
Max Act: 2.5307. Min Act: -0.1700
Data Index: 5561042 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5791. Min Range: -2.5791
Max Act: 2.4983. Min Act: -0.1700
Data Index: 5614559 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5791. Min Range: -2.5791
Max Act: 2.4821. Min Act: -0.1700
Data Index: 4319516 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5791. Min Range: -2.5791
Max Act: 2.4496. Min Act: -0.1700
Data Index: 6183348 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5791. Min Range: -2.5791
Max Act: 2.4821. Min Act: -0.1700
Data Index: 1003426 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5791. Min Range: -2.5791
Max Act: 2.4496. Min Act: -0.1700
Data Index: 6090292 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5791. Min Range: -2.5791
Max Act: 2.4496. Min Act: -0.1700
Data Index: 6100792 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5791. Min Range: -2.5791
Max Act: 2.4496. Min Act: -0.1700
Data Index: 7180211 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5791. Min Range: -2.5791
Max Act: 2.4496. Min Act: -0.1700
Data Index: 4435488 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5791. Min Range: -2.5791
Max Act: 2.4496. Min Act: -0.1700
Data Index: 5252186 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5791. Min Range: -2.5791
Max Act: 2.4334. Min Act: -0.1700
Data Index: 5841562 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5791. Min Range: -2.5791
Max Act: 2.4334. Min Act: -0.1700
Data Index: 2645659 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5791. Min Range: -2.5791
Max Act: 2.4171. Min Act: -0.1700
Data Index: 5450670 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5791. Min Range: -2.5791
Max Act: 2.4171. Min Act: -0.1700
Data Index: 7817792 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5791. Min Range: -2.5791
Max Act: 2.4171. Min Act: -0.1700
Data Index: 346499 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5791. Min Range: -2.5791
Max Act: 2.4171. Min Act: -0.1700
Data Index: 4443460 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5791. Min Range: -2.5791
Max Act: 2.4171. Min Act: -0.1700
Data Index: 1064846 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5791. Min Range: -2.5791
Max Act: 2.4171. Min Act: -0.1700
Data Index: 3291484 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #19