Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3825 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.1508. Min Range: -2.1508
Max Act: 2.1508. Min Act: -0.1700
Data Index: 3457600 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1508. Min Range: -2.1508
Max Act: 2.1508. Min Act: -0.1700
Data Index: 8265315 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1508. Min Range: -2.1508
Max Act: 2.1341. Min Act: -0.1700
Data Index: 4828878 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1508. Min Range: -2.1508
Max Act: 2.1174. Min Act: -0.1700
Data Index: 2348235 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1508. Min Range: -2.1508
Max Act: 2.1174. Min Act: -0.1700
Data Index: 6577934 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1508. Min Range: -2.1508
Max Act: 2.0839. Min Act: -0.1700
Data Index: 6911397 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1508. Min Range: -2.1508
Max Act: 2.0672. Min Act: -0.1700
Data Index: 285802 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1508. Min Range: -2.1508
Max Act: 2.0839. Min Act: -0.1700
Data Index: 2348232 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1508. Min Range: -2.1508
Max Act: 2.0839. Min Act: -0.1700
Data Index: 632324 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1508. Min Range: -2.1508
Max Act: 2.1007. Min Act: -0.1700
Data Index: 7749285 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1508. Min Range: -2.1508
Max Act: 2.0672. Min Act: -0.1700
Data Index: 8643341 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1508. Min Range: -2.1508
Max Act: 2.0672. Min Act: -0.1700
Data Index: 5819614 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1508. Min Range: -2.1508
Max Act: 2.0672. Min Act: -0.1700
Data Index: 6741948 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1508. Min Range: -2.1508
Max Act: 2.0503. Min Act: -0.1700
Data Index: 2817093 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1508. Min Range: -2.1508
Max Act: 2.0503. Min Act: -0.1700
Data Index: 3786684 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1508. Min Range: -2.1508
Max Act: 2.0335. Min Act: -0.1700
Data Index: 4811090 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1508. Min Range: -2.1508
Max Act: 2.0503. Min Act: -0.1700
Data Index: 4307718 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1508. Min Range: -2.1508
Max Act: 2.0335. Min Act: -0.1700
Data Index: 3577568 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1508. Min Range: -2.1508
Max Act: 2.0167. Min Act: -0.1700
Data Index: 754194 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1508. Min Range: -2.1508
Max Act: 2.0335. Min Act: -0.1700
Data Index: 6113811 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #19