Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2788 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1343. Min Range: -5.1343
Max Act: 5.1343. Min Act: -0.1700
Data Index: 8109693 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1343. Min Range: -5.1343
Max Act: 5.1031. Min Act: -0.1700
Data Index: 1058811 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1343. Min Range: -5.1343
Max Act: 5.1031. Min Act: -0.1700
Data Index: 8127560 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1343. Min Range: -5.1343
Max Act: 5.1031. Min Act: -0.1700
Data Index: 3819634 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1343. Min Range: -5.1343
Max Act: 5.0718. Min Act: -0.1700
Data Index: 7369997 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1343. Min Range: -5.1343
Max Act: 4.9781. Min Act: -0.1700
Data Index: 3360266 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1343. Min Range: -5.1343
Max Act: 4.9468. Min Act: -0.1700
Data Index: 1607383 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1343. Min Range: -5.1343
Max Act: 4.9156. Min Act: -0.1700
Data Index: 2690797 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1343. Min Range: -5.1343
Max Act: 4.8843. Min Act: -0.1700
Data Index: 309404 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1343. Min Range: -5.1343
Max Act: 4.8843. Min Act: -0.1700
Data Index: 8232433 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1343. Min Range: -5.1343
Max Act: 4.8218. Min Act: -0.1700
Data Index: 4469141 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1343. Min Range: -5.1343
Max Act: 4.8218. Min Act: -0.1700
Data Index: 2980743 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1343. Min Range: -5.1343
Max Act: 4.8218. Min Act: -0.1700
Data Index: 2595989 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1343. Min Range: -5.1343
Max Act: 4.8218. Min Act: -0.1700
Data Index: 5194108 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1343. Min Range: -5.1343
Max Act: 4.8218. Min Act: -0.1700
Data Index: 4704926 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1343. Min Range: -5.1343
Max Act: 4.7906. Min Act: -0.1700
Data Index: 1513463 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1343. Min Range: -5.1343
Max Act: 4.7906. Min Act: -0.1700
Data Index: 2809539 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1343. Min Range: -5.1343
Max Act: 4.7906. Min Act: -0.1700
Data Index: 1914431 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1343. Min Range: -5.1343
Max Act: 4.7906. Min Act: -0.1700
Data Index: 3665440 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1343. Min Range: -5.1343
Max Act: 4.7593. Min Act: -0.1700
Data Index: 3547590 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #19