Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3116 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4056. Min Range: -6.4056
Max Act: 6.4056. Min Act: -0.1700
Data Index: 491993 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4056. Min Range: -6.4056
Max Act: 6.2493. Min Act: -0.1700
Data Index: 5293192 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4056. Min Range: -6.4056
Max Act: 6.2493. Min Act: -0.1700
Data Index: 4943528 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4056. Min Range: -6.4056
Max Act: 6.1868. Min Act: -0.1700
Data Index: 4338696 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4056. Min Range: -6.4056
Max Act: 6.0618. Min Act: -0.1700
Data Index: 6285021 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4056. Min Range: -6.4056
Max Act: 6.0618. Min Act: -0.1700
Data Index: 6112023 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4056. Min Range: -6.4056
Max Act: 6.0306. Min Act: -0.1700
Data Index: 3145137 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4056. Min Range: -6.4056
Max Act: 5.9993. Min Act: -0.1700
Data Index: 5770560 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4056. Min Range: -6.4056
Max Act: 5.9993. Min Act: -0.1700
Data Index: 8449650 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4056. Min Range: -6.4056
Max Act: 5.9993. Min Act: -0.1700
Data Index: 3667478 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4056. Min Range: -6.4056
Max Act: 5.9681. Min Act: -0.1700
Data Index: 3472098 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4056. Min Range: -6.4056
Max Act: 5.9681. Min Act: -0.1700
Data Index: 1993743 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4056. Min Range: -6.4056
Max Act: 5.9368. Min Act: -0.1700
Data Index: 4458274 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4056. Min Range: -6.4056
Max Act: 5.8743. Min Act: -0.1700
Data Index: 1526740 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4056. Min Range: -6.4056
Max Act: 5.8743. Min Act: -0.1700
Data Index: 5510212 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4056. Min Range: -6.4056
Max Act: 5.8743. Min Act: -0.1700
Data Index: 4218590 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4056. Min Range: -6.4056
Max Act: 5.8431. Min Act: -0.1700
Data Index: 5180658 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4056. Min Range: -6.4056
Max Act: 5.8431. Min Act: -0.1700
Data Index: 6895429 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4056. Min Range: -6.4056
Max Act: 5.8431. Min Act: -0.1700
Data Index: 2995740 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4056. Min Range: -6.4056
Max Act: 5.8118. Min Act: -0.1700
Data Index: 8129223 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #19