Model: None
Dataset: The Pile
Neuron 4067 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 3.2206. Min Range: -3.2206
Max Act: 3.2206. Min Act: -0.1700
Data Index: 1656203 (The Pile)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2206. Min Range: -3.2206
Max Act: 3.1576. Min Act: -0.1700
Data Index: 404947 (The Pile)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2206. Min Range: -3.2206
Max Act: 3.0946. Min Act: -0.1700
Data Index: 4147901 (The Pile)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2206. Min Range: -3.2206
Max Act: 3.0788. Min Act: -0.1700
Data Index: 3763444 (The Pile)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2206. Min Range: -3.2206
Max Act: 3.0631. Min Act: -0.1700
Data Index: 527638 (The Pile)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2206. Min Range: -3.2206
Max Act: 2.9999. Min Act: -0.1700
Data Index: 2038810 (The Pile)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2206. Min Range: -3.2206
Max Act: 2.9841. Min Act: -0.1700
Data Index: 3239311 (The Pile)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2206. Min Range: -3.2206
Max Act: 2.9841. Min Act: -0.1700
Data Index: 5975784 (The Pile)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2206. Min Range: -3.2206
Max Act: 2.9841. Min Act: -0.1700
Data Index: 7446623 (The Pile)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2206. Min Range: -3.2206
Max Act: 2.9841. Min Act: -0.1700
Data Index: 9647044 (The Pile)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2206. Min Range: -3.2206
Max Act: 2.9682. Min Act: -0.1700
Data Index: 1320544 (The Pile)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2206. Min Range: -3.2206
Max Act: 2.9682. Min Act: -0.1700
Data Index: 5597614 (The Pile)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2206. Min Range: -3.2206
Max Act: 2.9682. Min Act: -0.1700
Data Index: 10457422 (The Pile)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2206. Min Range: -3.2206
Max Act: 2.9524. Min Act: -0.1700
Data Index: 5402328 (The Pile)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2206. Min Range: -3.2206
Max Act: 2.9524. Min Act: -0.1700
Data Index: 5294150 (The Pile)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2206. Min Range: -3.2206
Max Act: 2.9524. Min Act: -0.1700
Data Index: 9686448 (The Pile)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2206. Min Range: -3.2206
Max Act: 2.9524. Min Act: -0.1700
Data Index: 5534638 (The Pile)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2206. Min Range: -3.2206
Max Act: 2.9524. Min Act: -0.1700
Data Index: 5572317 (The Pile)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2206. Min Range: -3.2206
Max Act: 2.9524. Min Act: -0.1700
Data Index: 7462687 (The Pile)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2206. Min Range: -3.2206
Max Act: 2.9524. Min Act: -0.1700
Data Index: 929607 (The Pile)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #19