Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 362 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9530. Min Range: -4.9530
Max Act: 4.9530. Min Act: -0.1700
Data Index: 6896886 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9530. Min Range: -4.9530
Max Act: 4.9217. Min Act: -0.1700
Data Index: 6838181 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9530. Min Range: -4.9530
Max Act: 4.8280. Min Act: -0.1700
Data Index: 7380763 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9530. Min Range: -4.9530
Max Act: 4.7967. Min Act: -0.1700
Data Index: 7090539 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9530. Min Range: -4.9530
Max Act: 4.7967. Min Act: -0.1700
Data Index: 3500636 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9530. Min Range: -4.9530
Max Act: 4.7342. Min Act: -0.1700
Data Index: 8657062 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9530. Min Range: -4.9530
Max Act: 4.6717. Min Act: -0.1700
Data Index: 4752953 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9530. Min Range: -4.9530
Max Act: 4.6405. Min Act: -0.1700
Data Index: 4012411 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9530. Min Range: -4.9530
Max Act: 4.6405. Min Act: -0.1700
Data Index: 7184489 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9530. Min Range: -4.9530
Max Act: 4.6405. Min Act: -0.1700
Data Index: 8109581 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9530. Min Range: -4.9530
Max Act: 4.5467. Min Act: -0.1700
Data Index: 1114245 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9530. Min Range: -4.9530
Max Act: 4.5467. Min Act: -0.1700
Data Index: 7350394 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9530. Min Range: -4.9530
Max Act: 4.5467. Min Act: -0.1700
Data Index: 2240605 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9530. Min Range: -4.9530
Max Act: 4.5155. Min Act: -0.1700
Data Index: 8588251 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9530. Min Range: -4.9530
Max Act: 4.5155. Min Act: -0.1700
Data Index: 7400236 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9530. Min Range: -4.9530
Max Act: 4.5155. Min Act: -0.1700
Data Index: 6182572 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9530. Min Range: -4.9530
Max Act: 4.4842. Min Act: -0.1700
Data Index: 4634469 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9530. Min Range: -4.9530
Max Act: 4.4530. Min Act: -0.1700
Data Index: 1534210 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9530. Min Range: -4.9530
Max Act: 4.4842. Min Act: -0.1700
Data Index: 46756 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9530. Min Range: -4.9530
Max Act: 4.4842. Min Act: -0.1700
Data Index: 1041075 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #19