Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2958 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5288. Min Range: -9.5288
Max Act: 9.5288. Min Act: -0.1700
Data Index: 3107492 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5288. Min Range: -9.5288
Max Act: 9.4038. Min Act: -0.1700
Data Index: 5069246 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5288. Min Range: -9.5288
Max Act: 9.3413. Min Act: -0.1700
Data Index: 452364 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5288. Min Range: -9.5288
Max Act: 9.2788. Min Act: -0.1700
Data Index: 1705787 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5288. Min Range: -9.5288
Max Act: 9.2163. Min Act: -0.1700
Data Index: 5069247 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5288. Min Range: -9.5288
Max Act: 9.0913. Min Act: -0.1700
Data Index: 3107495 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5288. Min Range: -9.5288
Max Act: 9.0913. Min Act: -0.1700
Data Index: 5069255 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5288. Min Range: -9.5288
Max Act: 9.0288. Min Act: -0.1700
Data Index: 3107498 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5288. Min Range: -9.5288
Max Act: 9.0288. Min Act: -0.1700
Data Index: 5069245 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5288. Min Range: -9.5288
Max Act: 9.0288. Min Act: -0.1700
Data Index: 87503 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5288. Min Range: -9.5288
Max Act: 8.9663. Min Act: -0.1700
Data Index: 5069248 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5288. Min Range: -9.5288
Max Act: 8.9663. Min Act: -0.1700
Data Index: 5069253 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5288. Min Range: -9.5288
Max Act: 8.9663. Min Act: -0.1700
Data Index: 3107478 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5288. Min Range: -9.5288
Max Act: 8.9663. Min Act: -0.1700
Data Index: 3107493 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5288. Min Range: -9.5288
Max Act: 8.9663. Min Act: -0.1700
Data Index: 5069254 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5288. Min Range: -9.5288
Max Act: 8.9038. Min Act: -0.1700
Data Index: 3107481 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5288. Min Range: -9.5288
Max Act: 8.9038. Min Act: -0.1700
Data Index: 3107496 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5288. Min Range: -9.5288
Max Act: 8.8413. Min Act: -0.1700
Data Index: 3107479 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5288. Min Range: -9.5288
Max Act: 8.8413. Min Act: -0.1700
Data Index: 87510 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5288. Min Range: -9.5288
Max Act: 8.8413. Min Act: -0.1700
Data Index: 87521 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #19