Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3033 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2979. Min Range: -5.2979
Max Act: 5.2979. Min Act: -0.1700
Data Index: 8129351 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2979. Min Range: -5.2979
Max Act: 5.2354. Min Act: -0.1700
Data Index: 3555380 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2979. Min Range: -5.2979
Max Act: 5.1416. Min Act: -0.1700
Data Index: 2240352 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2979. Min Range: -5.2979
Max Act: 5.1104. Min Act: -0.1700
Data Index: 4725821 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2979. Min Range: -5.2979
Max Act: 5.1104. Min Act: -0.1700
Data Index: 8211245 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2979. Min Range: -5.2979
Max Act: 5.0791. Min Act: -0.1700
Data Index: 5685907 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2979. Min Range: -5.2979
Max Act: 5.0791. Min Act: -0.1700
Data Index: 4659591 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2979. Min Range: -5.2979
Max Act: 5.0479. Min Act: -0.1700
Data Index: 3156618 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2979. Min Range: -5.2979
Max Act: 5.0166. Min Act: -0.1700
Data Index: 717756 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2979. Min Range: -5.2979
Max Act: 5.0166. Min Act: -0.1700
Data Index: 7956200 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2979. Min Range: -5.2979
Max Act: 5.0166. Min Act: -0.1700
Data Index: 756187 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2979. Min Range: -5.2979
Max Act: 5.0479. Min Act: -0.1700
Data Index: 4198257 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2979. Min Range: -5.2979
Max Act: 4.9854. Min Act: -0.1700
Data Index: 1490660 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2979. Min Range: -5.2979
Max Act: 4.9854. Min Act: -0.1700
Data Index: 8257294 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2979. Min Range: -5.2979
Max Act: 4.9854. Min Act: -0.1700
Data Index: 8347382 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2979. Min Range: -5.2979
Max Act: 4.9541. Min Act: -0.1700
Data Index: 8164107 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2979. Min Range: -5.2979
Max Act: 4.9541. Min Act: -0.1700
Data Index: 1350056 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2979. Min Range: -5.2979
Max Act: 4.9229. Min Act: -0.1700
Data Index: 4750291 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2979. Min Range: -5.2979
Max Act: 4.9229. Min Act: -0.1700
Data Index: 7262308 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2979. Min Range: -5.2979
Max Act: 4.9229. Min Act: -0.1700
Data Index: 4628573 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #19