Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5321 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9119. Min Range: -5.9119
Max Act: 5.9119. Min Act: -0.1700
Data Index: 4819847 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9119. Min Range: -5.9119
Max Act: 5.7557. Min Act: -0.1700
Data Index: 7579480 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9119. Min Range: -5.9119
Max Act: 5.6932. Min Act: -0.1700
Data Index: 4579252 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9119. Min Range: -5.9119
Max Act: 5.6932. Min Act: -0.1700
Data Index: 113411 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9119. Min Range: -5.9119
Max Act: 5.6619. Min Act: -0.1700
Data Index: 4960632 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9119. Min Range: -5.9119
Max Act: 5.6307. Min Act: -0.1700
Data Index: 8029451 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9119. Min Range: -5.9119
Max Act: 5.6307. Min Act: -0.1700
Data Index: 1416678 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9119. Min Range: -5.9119
Max Act: 5.5994. Min Act: -0.1700
Data Index: 6728284 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9119. Min Range: -5.9119
Max Act: 5.5682. Min Act: -0.1700
Data Index: 3252157 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9119. Min Range: -5.9119
Max Act: 5.5682. Min Act: -0.1700
Data Index: 4561315 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9119. Min Range: -5.9119
Max Act: 5.5682. Min Act: -0.1700
Data Index: 893286 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9119. Min Range: -5.9119
Max Act: 5.5682. Min Act: -0.1700
Data Index: 7437428 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9119. Min Range: -5.9119
Max Act: 5.5369. Min Act: -0.1700
Data Index: 74412 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9119. Min Range: -5.9119
Max Act: 5.5369. Min Act: -0.1700
Data Index: 1035165 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9119. Min Range: -5.9119
Max Act: 5.5369. Min Act: -0.1700
Data Index: 2703306 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9119. Min Range: -5.9119
Max Act: 5.5369. Min Act: -0.1700
Data Index: 4281866 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9119. Min Range: -5.9119
Max Act: 5.5057. Min Act: -0.1700
Data Index: 3445973 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9119. Min Range: -5.9119
Max Act: 5.5369. Min Act: -0.1700
Data Index: 8200671 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9119. Min Range: -5.9119
Max Act: 5.5057. Min Act: -0.1700
Data Index: 1183896 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9119. Min Range: -5.9119
Max Act: 5.5057. Min Act: -0.1700
Data Index: 6064968 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #19