Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3874 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5682. Min Range: -9.5682
Max Act: 9.5682. Min Act: -0.1700
Data Index: 8231337 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5682. Min Range: -9.5682
Max Act: 9.5057. Min Act: -0.1700
Data Index: 6281523 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5682. Min Range: -9.5682
Max Act: 9.2557. Min Act: -0.1700
Data Index: 4138889 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5682. Min Range: -9.5682
Max Act: 9.1932. Min Act: -0.1700
Data Index: 4031137 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5682. Min Range: -9.5682
Max Act: 9.1307. Min Act: -0.1700
Data Index: 4288514 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5682. Min Range: -9.5682
Max Act: 9.0057. Min Act: -0.1700
Data Index: 6307484 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5682. Min Range: -9.5682
Max Act: 9.0057. Min Act: -0.1700
Data Index: 261618 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5682. Min Range: -9.5682
Max Act: 8.9432. Min Act: -0.1700
Data Index: 6299316 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5682. Min Range: -9.5682
Max Act: 8.7557. Min Act: -0.1700
Data Index: 3930127 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5682. Min Range: -9.5682
Max Act: 8.8182. Min Act: -0.1700
Data Index: 6717975 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5682. Min Range: -9.5682
Max Act: 8.8182. Min Act: -0.1700
Data Index: 8002959 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5682. Min Range: -9.5682
Max Act: 8.7557. Min Act: -0.1700
Data Index: 93193 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5682. Min Range: -9.5682
Max Act: 8.7557. Min Act: -0.1700
Data Index: 6566099 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5682. Min Range: -9.5682
Max Act: 8.6932. Min Act: -0.1700
Data Index: 3242319 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5682. Min Range: -9.5682
Max Act: 8.6932. Min Act: -0.1700
Data Index: 6586252 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5682. Min Range: -9.5682
Max Act: 8.6932. Min Act: -0.1700
Data Index: 8129872 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5682. Min Range: -9.5682
Max Act: 8.6932. Min Act: -0.1700
Data Index: 3638862 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5682. Min Range: -9.5682
Max Act: 8.6932. Min Act: -0.1700
Data Index: 6164782 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5682. Min Range: -9.5682
Max Act: 8.6307. Min Act: -0.1700
Data Index: 1068693 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5682. Min Range: -9.5682
Max Act: 8.6307. Min Act: -0.1700
Data Index: 807346 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #19