Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3118 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7607. Min Range: -3.7607
Max Act: 3.7607. Min Act: -0.1700
Data Index: 2465014 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7607. Min Range: -3.7607
Max Act: 3.5572. Min Act: -0.1700
Data Index: 8037453 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7607. Min Range: -3.7607
Max Act: 3.5416. Min Act: -0.1700
Data Index: 1739772 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7607. Min Range: -3.7607
Max Act: 3.5103. Min Act: -0.1700
Data Index: 7339626 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7607. Min Range: -3.7607
Max Act: 3.4946. Min Act: -0.1700
Data Index: 1632113 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7607. Min Range: -3.7607
Max Act: 3.4946. Min Act: -0.1700
Data Index: 2788498 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7607. Min Range: -3.7607
Max Act: 3.4633. Min Act: -0.1700
Data Index: 445197 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7607. Min Range: -3.7607
Max Act: 3.4476. Min Act: -0.1700
Data Index: 7496802 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7607. Min Range: -3.7607
Max Act: 3.4319. Min Act: -0.1700
Data Index: 5156076 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7607. Min Range: -3.7607
Max Act: 3.4319. Min Act: -0.1700
Data Index: 1226711 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7607. Min Range: -3.7607
Max Act: 3.4006. Min Act: -0.1700
Data Index: 2551267 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7607. Min Range: -3.7607
Max Act: 3.4163. Min Act: -0.1700
Data Index: 1568895 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7607. Min Range: -3.7607
Max Act: 3.3692. Min Act: -0.1700
Data Index: 7091474 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7607. Min Range: -3.7607
Max Act: 3.3692. Min Act: -0.1700
Data Index: 4095943 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7607. Min Range: -3.7607
Max Act: 3.3692. Min Act: -0.1700
Data Index: 1795571 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7607. Min Range: -3.7607
Max Act: 3.3535. Min Act: -0.1700
Data Index: 2047779 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7607. Min Range: -3.7607
Max Act: 3.3535. Min Act: -0.1700
Data Index: 4628551 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7607. Min Range: -3.7607
Max Act: 3.3535. Min Act: -0.1700
Data Index: 3466606 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7607. Min Range: -3.7607
Max Act: 3.3379. Min Act: -0.1700
Data Index: 2877366 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7607. Min Range: -3.7607
Max Act: 3.3379. Min Act: -0.1700
Data Index: 2533032 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #19