Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4946 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0693. Min Range: -5.0693
Max Act: 5.0693. Min Act: -0.1700
Data Index: 1958130 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0693. Min Range: -5.0693
Max Act: 5.0693. Min Act: -0.1700
Data Index: 2995496 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0693. Min Range: -5.0693
Max Act: 5.0068. Min Act: -0.1700
Data Index: 169303 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0693. Min Range: -5.0693
Max Act: 5.0381. Min Act: -0.1700
Data Index: 2545334 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0693. Min Range: -5.0693
Max Act: 5.0381. Min Act: -0.1700
Data Index: 8132930 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0693. Min Range: -5.0693
Max Act: 5.0068. Min Act: -0.1700
Data Index: 4241530 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0693. Min Range: -5.0693
Max Act: 5.0068. Min Act: -0.1700
Data Index: 6902433 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0693. Min Range: -5.0693
Max Act: 4.9443. Min Act: -0.1700
Data Index: 2146481 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0693. Min Range: -5.0693
Max Act: 4.9443. Min Act: -0.1700
Data Index: 5223636 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0693. Min Range: -5.0693
Max Act: 4.9131. Min Act: -0.1694
Data Index: 7045972 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0693. Min Range: -5.0693
Max Act: 4.8818. Min Act: -0.1700
Data Index: 7090101 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0693. Min Range: -5.0693
Max Act: 4.9131. Min Act: -0.1700
Data Index: 7624580 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0693. Min Range: -5.0693
Max Act: 4.9131. Min Act: -0.1700
Data Index: 7179077 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0693. Min Range: -5.0693
Max Act: 4.8818. Min Act: -0.1695
Data Index: 110047 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0693. Min Range: -5.0693
Max Act: 4.8818. Min Act: -0.1700
Data Index: 7010807 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0693. Min Range: -5.0693
Max Act: 4.8506. Min Act: -0.1700
Data Index: 5430445 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0693. Min Range: -5.0693
Max Act: 4.8506. Min Act: -0.1700
Data Index: 5958893 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0693. Min Range: -5.0693
Max Act: 4.8506. Min Act: -0.1700
Data Index: 2760886 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0693. Min Range: -5.0693
Max Act: 4.8506. Min Act: -0.1700
Data Index: 3025393 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0693. Min Range: -5.0693
Max Act: 4.8506. Min Act: -0.1700
Data Index: 7004145 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #19