Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3673 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.2627. Min Range: -3.2627
Max Act: 3.2627. Min Act: -0.1700
Data Index: 2063650 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2627. Min Range: -3.2627
Max Act: 3.1999. Min Act: -0.1700
Data Index: 772385 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2627. Min Range: -3.2627
Max Act: 3.1999. Min Act: -0.1700
Data Index: 5482281 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2627. Min Range: -3.2627
Max Act: 3.1684. Min Act: -0.1700
Data Index: 5655195 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2627. Min Range: -3.2627
Max Act: 3.1999. Min Act: -0.1700
Data Index: 2087974 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2627. Min Range: -3.2627
Max Act: 3.1999. Min Act: -0.1700
Data Index: 5776112 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2627. Min Range: -3.2627
Max Act: 3.1999. Min Act: -0.1700
Data Index: 7328361 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2627. Min Range: -3.2627
Max Act: 3.1999. Min Act: -0.1700
Data Index: 2454957 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2627. Min Range: -3.2627
Max Act: 3.1684. Min Act: -0.1700
Data Index: 4626967 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2627. Min Range: -3.2627
Max Act: 3.1684. Min Act: -0.1700
Data Index: 1991960 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2627. Min Range: -3.2627
Max Act: 3.1684. Min Act: -0.1700
Data Index: 8822472 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2627. Min Range: -3.2627
Max Act: 3.1684. Min Act: -0.1700
Data Index: 1023384 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2627. Min Range: -3.2627
Max Act: 3.1684. Min Act: -0.1700
Data Index: 7124538 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2627. Min Range: -3.2627
Max Act: 3.1684. Min Act: -0.1700
Data Index: 5813969 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2627. Min Range: -3.2627
Max Act: 3.1369. Min Act: -0.1700
Data Index: 6866712 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2627. Min Range: -3.2627
Max Act: 3.1369. Min Act: -0.1700
Data Index: 3677841 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2627. Min Range: -3.2627
Max Act: 3.1369. Min Act: -0.1700
Data Index: 4270341 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2627. Min Range: -3.2627
Max Act: 3.1369. Min Act: -0.1700
Data Index: 2938196 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2627. Min Range: -3.2627
Max Act: 3.1369. Min Act: -0.1700
Data Index: 3397114 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2627. Min Range: -3.2627
Max Act: 3.1054. Min Act: -0.1700
Data Index: 671007 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19