Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3881 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3736. Min Range: -5.3736
Max Act: 5.3736. Min Act: -0.1700
Data Index: 247921 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3736. Min Range: -5.3736
Max Act: 5.2799. Min Act: -0.1700
Data Index: 1047089 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3736. Min Range: -5.3736
Max Act: 5.1549. Min Act: -0.1700
Data Index: 1136335 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3736. Min Range: -5.3736
Max Act: 5.1236. Min Act: -0.1700
Data Index: 4587824 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3736. Min Range: -5.3736
Max Act: 5.0924. Min Act: -0.1700
Data Index: 3775734 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3736. Min Range: -5.3736
Max Act: 5.0924. Min Act: -0.1700
Data Index: 1829920 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3736. Min Range: -5.3736
Max Act: 5.0924. Min Act: -0.1700
Data Index: 3250277 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3736. Min Range: -5.3736
Max Act: 4.9986. Min Act: -0.1700
Data Index: 1385438 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3736. Min Range: -5.3736
Max Act: 4.9986. Min Act: -0.1700
Data Index: 2378561 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3736. Min Range: -5.3736
Max Act: 4.9674. Min Act: -0.1700
Data Index: 3455971 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3736. Min Range: -5.3736
Max Act: 4.9674. Min Act: -0.1700
Data Index: 6703896 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3736. Min Range: -5.3736
Max Act: 4.9674. Min Act: -0.1700
Data Index: 6274416 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3736. Min Range: -5.3736
Max Act: 4.9674. Min Act: -0.1700
Data Index: 1415503 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3736. Min Range: -5.3736
Max Act: 4.9674. Min Act: -0.1700
Data Index: 1640350 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3736. Min Range: -5.3736
Max Act: 4.9674. Min Act: -0.1700
Data Index: 6042013 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3736. Min Range: -5.3736
Max Act: 4.9674. Min Act: -0.1700
Data Index: 151552 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3736. Min Range: -5.3736
Max Act: 4.9674. Min Act: -0.1700
Data Index: 3745231 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3736. Min Range: -5.3736
Max Act: 4.9361. Min Act: -0.1700
Data Index: 8695063 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3736. Min Range: -5.3736
Max Act: 4.9049. Min Act: -0.1700
Data Index: 3417023 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3736. Min Range: -5.3736
Max Act: 4.9049. Min Act: -0.1700
Data Index: 5801428 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #19