Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3511 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4711. Min Range: -5.4711
Max Act: 5.4711. Min Act: -0.1700
Data Index: 623145 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4711. Min Range: -5.4711
Max Act: 5.4086. Min Act: -0.1700
Data Index: 762389 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4711. Min Range: -5.4711
Max Act: 5.4086. Min Act: -0.1700
Data Index: 7988215 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4711. Min Range: -5.4711
Max Act: 5.3461. Min Act: -0.1700
Data Index: 5078565 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4711. Min Range: -5.4711
Max Act: 5.3461. Min Act: -0.1700
Data Index: 5471793 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4711. Min Range: -5.4711
Max Act: 5.2211. Min Act: -0.1700
Data Index: 7290624 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4711. Min Range: -5.4711
Max Act: 5.1899. Min Act: -0.1700
Data Index: 2973962 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4711. Min Range: -5.4711
Max Act: 5.1586. Min Act: -0.1700
Data Index: 3991536 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4711. Min Range: -5.4711
Max Act: 5.1899. Min Act: -0.1700
Data Index: 6855299 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4711. Min Range: -5.4711
Max Act: 5.1899. Min Act: -0.1700
Data Index: 6262259 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4711. Min Range: -5.4711
Max Act: 5.1586. Min Act: -0.1700
Data Index: 872140 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4711. Min Range: -5.4711
Max Act: 5.1586. Min Act: -0.1700
Data Index: 7477542 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4711. Min Range: -5.4711
Max Act: 5.1274. Min Act: -0.1700
Data Index: 7758722 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4711. Min Range: -5.4711
Max Act: 5.0961. Min Act: -0.1700
Data Index: 3582824 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4711. Min Range: -5.4711
Max Act: 5.0961. Min Act: -0.1700
Data Index: 4035069 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4711. Min Range: -5.4711
Max Act: 5.0961. Min Act: -0.1700
Data Index: 1951118 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4711. Min Range: -5.4711
Max Act: 5.0961. Min Act: -0.1700
Data Index: 5900237 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4711. Min Range: -5.4711
Max Act: 5.0649. Min Act: -0.1700
Data Index: 6924823 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4711. Min Range: -5.4711
Max Act: 5.0649. Min Act: -0.1700
Data Index: 7615881 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4711. Min Range: -5.4711
Max Act: 5.0649. Min Act: -0.1700
Data Index: 3323517 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #19