Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3065 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2979. Min Range: -7.2979
Max Act: 7.2979. Min Act: -0.1700
Data Index: 3361621 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2979. Min Range: -7.2979
Max Act: 7.1417. Min Act: -0.1700
Data Index: 6515545 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2979. Min Range: -7.2979
Max Act: 7.0479. Min Act: -0.1700
Data Index: 6222195 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2979. Min Range: -7.2979
Max Act: 7.0479. Min Act: -0.1700
Data Index: 4544696 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2979. Min Range: -7.2979
Max Act: 7.0167. Min Act: -0.1700
Data Index: 7960360 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2979. Min Range: -7.2979
Max Act: 6.9854. Min Act: -0.1700
Data Index: 8683949 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2979. Min Range: -7.2979
Max Act: 7.0167. Min Act: -0.1700
Data Index: 3118735 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2979. Min Range: -7.2979
Max Act: 6.9542. Min Act: -0.1700
Data Index: 8633888 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2979. Min Range: -7.2979
Max Act: 6.8917. Min Act: -0.1700
Data Index: 8552288 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2979. Min Range: -7.2979
Max Act: 6.8917. Min Act: -0.1700
Data Index: 3637411 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2979. Min Range: -7.2979
Max Act: 6.8292. Min Act: -0.1700
Data Index: 2854310 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2979. Min Range: -7.2979
Max Act: 6.7979. Min Act: -0.1700
Data Index: 4961417 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2979. Min Range: -7.2979
Max Act: 6.7979. Min Act: -0.1700
Data Index: 4951485 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2979. Min Range: -7.2979
Max Act: 6.7667. Min Act: -0.1700
Data Index: 189389 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2979. Min Range: -7.2979
Max Act: 6.7042. Min Act: -0.1700
Data Index: 7276190 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2979. Min Range: -7.2979
Max Act: 6.7042. Min Act: -0.1700
Data Index: 2252104 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2979. Min Range: -7.2979
Max Act: 6.7042. Min Act: -0.1700
Data Index: 3252318 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2979. Min Range: -7.2979
Max Act: 6.6729. Min Act: -0.1700
Data Index: 1259667 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2979. Min Range: -7.2979
Max Act: 6.6417. Min Act: -0.1700
Data Index: 1061312 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2979. Min Range: -7.2979
Max Act: 6.6417. Min Act: -0.1700
Data Index: 167608 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #19