Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2820 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5059. Min Range: -5.5059
Max Act: 5.5059. Min Act: -0.1700
Data Index: 7704109 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5059. Min Range: -5.5059
Max Act: 5.4747. Min Act: -0.1700
Data Index: 5290633 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5059. Min Range: -5.5059
Max Act: 5.3809. Min Act: -0.1700
Data Index: 1912049 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5059. Min Range: -5.5059
Max Act: 5.3497. Min Act: -0.1700
Data Index: 5275409 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5059. Min Range: -5.5059
Max Act: 5.3497. Min Act: -0.1700
Data Index: 7190428 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5059. Min Range: -5.5059
Max Act: 5.3184. Min Act: -0.1700
Data Index: 2919332 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5059. Min Range: -5.5059
Max Act: 5.2872. Min Act: -0.1700
Data Index: 3802964 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5059. Min Range: -5.5059
Max Act: 5.2872. Min Act: -0.1700
Data Index: 4814582 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5059. Min Range: -5.5059
Max Act: 5.2872. Min Act: -0.1700
Data Index: 7087281 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5059. Min Range: -5.5059
Max Act: 5.2872. Min Act: -0.1700
Data Index: 1956211 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5059. Min Range: -5.5059
Max Act: 5.2559. Min Act: -0.1700
Data Index: 4380220 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5059. Min Range: -5.5059
Max Act: 5.2872. Min Act: -0.1700
Data Index: 6444601 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5059. Min Range: -5.5059
Max Act: 5.2559. Min Act: -0.1700
Data Index: 3033887 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5059. Min Range: -5.5059
Max Act: 5.2559. Min Act: -0.1700
Data Index: 4793431 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5059. Min Range: -5.5059
Max Act: 5.2559. Min Act: -0.1700
Data Index: 7877041 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5059. Min Range: -5.5059
Max Act: 5.2559. Min Act: -0.1700
Data Index: 7789572 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5059. Min Range: -5.5059
Max Act: 5.2872. Min Act: -0.1700
Data Index: 7392435 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5059. Min Range: -5.5059
Max Act: 5.2559. Min Act: -0.1700
Data Index: 7070105 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5059. Min Range: -5.5059
Max Act: 5.2247. Min Act: -0.1700
Data Index: 2881886 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5059. Min Range: -5.5059
Max Act: 5.2247. Min Act: -0.1700
Data Index: 10751 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #19