Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2775 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3472. Min Range: -3.3472
Max Act: 3.3472. Min Act: -0.1700
Data Index: 2067085 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3472. Min Range: -3.3472
Max Act: 3.3472. Min Act: -0.1700
Data Index: 5660454 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3472. Min Range: -3.3472
Max Act: 3.3472. Min Act: -0.1700
Data Index: 4299048 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3472. Min Range: -3.3472
Max Act: 3.3158. Min Act: -0.1700
Data Index: 3660694 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3472. Min Range: -3.3472
Max Act: 3.3158. Min Act: -0.1700
Data Index: 7900202 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3472. Min Range: -3.3472
Max Act: 3.3158. Min Act: -0.1700
Data Index: 1638401 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3472. Min Range: -3.3472
Max Act: 3.3158. Min Act: -0.1700
Data Index: 1408734 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3472. Min Range: -3.3472
Max Act: 3.2844. Min Act: -0.1700
Data Index: 7616687 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3472. Min Range: -3.3472
Max Act: 3.2844. Min Act: -0.1700
Data Index: 7742063 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3472. Min Range: -3.3472
Max Act: 3.2844. Min Act: -0.1700
Data Index: 678055 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3472. Min Range: -3.3472
Max Act: 3.2844. Min Act: -0.1700
Data Index: 6009430 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3472. Min Range: -3.3472
Max Act: 3.2844. Min Act: -0.1700
Data Index: 6842216 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3472. Min Range: -3.3472
Max Act: 3.2844. Min Act: -0.1700
Data Index: 8755849 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3472. Min Range: -3.3472
Max Act: 3.2687. Min Act: -0.1700
Data Index: 1830532 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3472. Min Range: -3.3472
Max Act: 3.2530. Min Act: -0.1700
Data Index: 3552000 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3472. Min Range: -3.3472
Max Act: 3.2530. Min Act: -0.1700
Data Index: 3159989 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3472. Min Range: -3.3472
Max Act: 3.2530. Min Act: -0.1700
Data Index: 3273145 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3472. Min Range: -3.3472
Max Act: 3.2530. Min Act: -0.1700
Data Index: 6195829 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3472. Min Range: -3.3472
Max Act: 3.2530. Min Act: -0.1700
Data Index: 7600910 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3472. Min Range: -3.3472
Max Act: 3.2530. Min Act: -0.1700
Data Index: 2641559 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #19