Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2948 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2088. Min Range: -3.2088
Max Act: 3.2088. Min Act: -0.1700
Data Index: 5579157 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2088. Min Range: -3.2088
Max Act: 3.1616. Min Act: -0.1700
Data Index: 4133785 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2088. Min Range: -3.2088
Max Act: 3.1459. Min Act: -0.1700
Data Index: 6567964 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2088. Min Range: -3.2088
Max Act: 3.0671. Min Act: -0.1700
Data Index: 5272042 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2088. Min Range: -3.2088
Max Act: 2.9881. Min Act: -0.1700
Data Index: 6400249 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2088. Min Range: -3.2088
Max Act: 2.9565. Min Act: -0.1700
Data Index: 6028132 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2088. Min Range: -3.2088
Max Act: 2.9565. Min Act: -0.1700
Data Index: 3416134 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2088. Min Range: -3.2088
Max Act: 2.9565. Min Act: -0.1700
Data Index: 5940069 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2088. Min Range: -3.2088
Max Act: 2.9407. Min Act: -0.1700
Data Index: 6912396 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2088. Min Range: -3.2088
Max Act: 2.9565. Min Act: -0.1700
Data Index: 7136899 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2088. Min Range: -3.2088
Max Act: 2.9407. Min Act: -0.1700
Data Index: 6842849 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2088. Min Range: -3.2088
Max Act: 2.9565. Min Act: -0.1700
Data Index: 446875 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2088. Min Range: -3.2088
Max Act: 2.9248. Min Act: -0.1700
Data Index: 4751558 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2088. Min Range: -3.2088
Max Act: 2.9248. Min Act: -0.1700
Data Index: 1410559 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2088. Min Range: -3.2088
Max Act: 2.9090. Min Act: -0.1700
Data Index: 5034910 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2088. Min Range: -3.2088
Max Act: 2.8931. Min Act: -0.1700
Data Index: 5707096 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2088. Min Range: -3.2088
Max Act: 2.9090. Min Act: -0.1700
Data Index: 3403997 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2088. Min Range: -3.2088
Max Act: 2.8931. Min Act: -0.1700
Data Index: 1984997 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2088. Min Range: -3.2088
Max Act: 2.8931. Min Act: -0.1700
Data Index: 4983182 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2088. Min Range: -3.2088
Max Act: 2.8773. Min Act: -0.1700
Data Index: 1657070 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #19