Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6103 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4131. Min Range: -5.4131
Max Act: 5.4131. Min Act: -0.1700
Data Index: 5314577 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4131. Min Range: -5.4131
Max Act: 5.3818. Min Act: -0.1700
Data Index: 3868984 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4131. Min Range: -5.4131
Max Act: 5.3193. Min Act: -0.1700
Data Index: 3679329 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4131. Min Range: -5.4131
Max Act: 5.1943. Min Act: -0.1700
Data Index: 4325488 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4131. Min Range: -5.4131
Max Act: 5.1631. Min Act: -0.1700
Data Index: 7753909 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4131. Min Range: -5.4131
Max Act: 5.1631. Min Act: -0.1700
Data Index: 5946538 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4131. Min Range: -5.4131
Max Act: 5.1318. Min Act: -0.1700
Data Index: 2914171 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4131. Min Range: -5.4131
Max Act: 5.1006. Min Act: -0.1700
Data Index: 6569454 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4131. Min Range: -5.4131
Max Act: 5.0381. Min Act: -0.1700
Data Index: 2812038 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4131. Min Range: -5.4131
Max Act: 5.0693. Min Act: -0.1700
Data Index: 4875839 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4131. Min Range: -5.4131
Max Act: 5.0693. Min Act: -0.1700
Data Index: 2728531 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4131. Min Range: -5.4131
Max Act: 5.1006. Min Act: -0.1700
Data Index: 7711782 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4131. Min Range: -5.4131
Max Act: 5.0381. Min Act: -0.1700
Data Index: 4815422 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4131. Min Range: -5.4131
Max Act: 5.0381. Min Act: -0.1700
Data Index: 7202884 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4131. Min Range: -5.4131
Max Act: 5.0381. Min Act: -0.1700
Data Index: 5844488 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4131. Min Range: -5.4131
Max Act: 5.0068. Min Act: -0.1700
Data Index: 7170430 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4131. Min Range: -5.4131
Max Act: 5.0068. Min Act: -0.1700
Data Index: 6198033 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4131. Min Range: -5.4131
Max Act: 4.9756. Min Act: -0.1700
Data Index: 3608499 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4131. Min Range: -5.4131
Max Act: 4.9443. Min Act: -0.1700
Data Index: 2754843 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4131. Min Range: -5.4131
Max Act: 4.9756. Min Act: -0.1700
Data Index: 7409700 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #19